Skip to contents

from a list of filtered text (from the function filter_by_query), tags the POS/ parse with spacyr. It also renumber the doc_id and sentence_id. It runs spacyr::entity_extract() or spacyr::entity_consolidate() in background, but also runs on lists with empty elements, and can returns a single dataframe (if `bind = TRUE`) renaming doc_id and sentence_id,

Usage

parsePOS(txt, bind = TRUE, only_entities = TRUE)

Arguments

txt

a list of filtered text

bind

if TRUE (default), returns a single dataframe. if FALSE, returns a List object

entities

if TRUE (default), returns only the entities. if FALSE, returns consolidated entities

Examples

txt_wiki |>
  filter_by_query("Police") |>
  parsePOS()
#>    doc_id sentence_id                                   entity entity_type
#> 1   text1           1                             Pennsylvania         GPE
#> 2   text1           1                               New_Jersey         GPE
#> 3   text2           1                         Ted_Kaczynski_'s      PERSON
#> 4   text2           1        Industrial_Society_and_Its_Future         ORG
#> 5   text1           2 the_George_Washington_Bridge_Bus_Station         ORG
#> 6   text1           2                          Upper_Manhattan         LOC
#> 7   text1           1                             Central_Park         LOC
#> 8   text1           1                            New_York_City         GPE
#> 9   text1           2                                 Mangione         ORG
#> 10  text1           2      the_San_Francisco_Police_Department         ORG
#> 11  text1           2                                 Mangione         ORG
#> 12  text1           2                            San_Francisco         GPE
#> 13  text1           1                                  Altoona         GPE
#> 14  text1           1                             Pennsylvania         GPE
#> 15  text1           1                                 Mangione         ORG
#> 16  text1           1                                 McDonald         ORG
#> 17  text2           1                                     NYPD         ORG
#> 18  text3           2                               New_Jersey         GPE
#> 19  text3           2                                Manhattan         GPE
#> 20  text4           1                                 American        NORP
#> 21  text1           1                                 Mangione         ORG
#> 22  text2           1                                 New_York         GPE
#> 23  text2           1                             Joseph_Kenny      PERSON
#> 24  text1           1                                 Mangione         ORG
#> 25  text1           1                         Ted_Kaczynski_'s      PERSON
#> 26  text1           1        Industrial_Society_and_Its_Future         ORG

txt_wiki |>
  filter_by_query("Police") |>
  parsePOS(only_entities = FALSE)
#>     doc_id sentence_id token_id                                    token
#> 1        4           1        1                                       11
#> 2        4           1        2                                        ]
#> 3        4           1        3                                 Mangione
#> 4        4           1        4                                      was
#> 5        4           1        5                                     held
#> 6        4           1        6                                  without
#> 7        4           1        7                                     bail
#> 8        4           1        8                                       in
#> 9        4           1        9                             Pennsylvania
#> 10       4           1       10                                       on
#> 11       4           1       11                                  charges
#> 12       4           1       12                                       of
#> 13       4           1       13                               possession
#> 14       4           1       14                                       of
#> 15       4           1       15                                       an
#> 16       4           1       16                               unlicensed
#> 17       4           1       17                                  firearm
#> 18       4           1       18                                        ,
#> 19       4           1       19                                  forgery
#> 20       4           1       20                                        ,
#> 21       4           1       21                                      and
#> 22       4           1       22                                providing
#> 23       4           1       23                                    false
#> 24       4           1       24                               New_Jersey
#> 25       4           1       25                                        -
#> 26       4           1       26                                 resident
#> 27       4           1       27                           identification
#> 28       4           1       28                                       to
#> 29       4           1       29                                   police
#> 30       4           1       30                                        .
#> 31       4           1        1                                        [
#> 32       4           2        1                                       12
#> 33       4           2        2                                        ]
#> 34       4           2        3                                   Police
#> 35       4           2        4                                  believe
#> 36       4           2        5                                     that
#> 37       4           2        6                                       he
#> 38       4           2        7                                      was
#> 39       4           2        8                                 inspired
#> 40       4           2        9                                       by
#> 41       4           2       10                         Ted_Kaczynski_'s
#> 42       4           2       11                                    essay
#> 43       4           2       12        Industrial_Society_and_Its_Future
#> 44       4           2       13                                        (
#> 45       4           2       14                                     1995
#> 46       4           2       15                                        )
#> 47       4           2       16                                        ,
#> 48       4           2       17                                      and
#> 49       4           2       18                                motivated
#> 50       4           2       19                                       by
#> 51       4           2       20                                      his
#> 52       4           2       21                                 personal
#> 53       4           2       22                                    views
#> 54       4           2       23                                       on
#> 55       4           2       24                                   health
#> 56       4           2       25                                insurance
#> 57       4           2       26                                        .
#> 58       4           2        1                                        [
#> 59      12           1        1                                       39
#> 60      12           1        2                                        ]
#> 61      12           1        1                                According
#> 62      12           1        2                                       to
#> 63      12           1        3                                      the
#> 64      12           1        4                                   police
#> 65      12           1        5                                        ,
#> 66      12           1        6                                       he
#> 67      12           1        7                                     then
#> 68      12           1        8                                     left
#> 69      12           1        9                                      the
#> 70      12           1       10                                     city
#> 71      12           1       11                                     from
#> 72      12           1       12 the_George_Washington_Bridge_Bus_Station
#> 73      12           1       13                                  farther
#> 74      12           1       14                                   uptown
#> 75      12           1       15                                       in
#> 76      12           1       16                          Upper_Manhattan
#> 77      12           1       17                                        .
#> 78      12           1        1                                        [
#> 79      13           1        1                                       49
#> 80      13           1        2                                        ]
#> 81      13           1        1                              Accordingly
#> 82      13           1        2                                        ,
#> 83      13           1        3                                   police
#> 84      13           1        4                                   stated
#> 85      13           1        5                                     they
#> 86      13           1        6                                      are
#> 87      13           1        7                            investigating
#> 88      13           1        8                                  whether
#> 89      13           1        9                                      the
#> 90      13           1       10                                    words
#> 91      13           1       11                                  suggest
#> 92      13           1       12                                      the
#> 93      13           1       13                                   killer
#> 94      13           1       14                                       's
#> 95      13           1       15                                   motive
#> 96      13           1       16                                        .
#> 97      13           1        1                                        [
#> 98      14           1        1                                       50
#> 99      14           1        2                                        ]
#> 100     14           1        3                                   Police
#> 101     14           1        4                                     said
#> 102     14           1        5                                     they
#> 103     14           1        6                                 believed
#> 104     14           1        7                                     they
#> 105     14           1        8                                    found
#> 106     14           1        9                                      the
#> 107     14           1       10                                  shooter
#> 108     14           1       11                                       's
#> 109     14           1       12                                 backpack
#> 110     14           1       13                                       in
#> 111     14           1       14                             Central_Park
#> 112     14           1       15                                       on
#> 113     14           1       16                        December_6_,_2024
#> 114     14           1       17                                        .
#> 115     14           1        1                                        [
#> 116     15           1        1                                      The
#> 117     15           1        2                            New_York_City
#> 118     15           1        3                                   Police
#> 119     15           1        4                               Department
#> 120     15           1        5                                  offered
#> 121     15           1        6                                        a
#> 122     15           1        7                                   reward
#> 123     15           1        8                           up_to_$_10,000
#> 124     15           1        9                                      for
#> 125     15           1       10                              information
#> 126     15           1       11                                    about
#> 127     15           1       12                                      the
#> 128     15           1       13                                  shooter
#> 129     15           1       14                                       on
#> 130     15           1       15                        December_4_,_2024
#> 131     15           1       16                                        .
#> 132     15           1        1                                        [
#> 133     16           1        1                                      The
#> 134     16           1        2                                  shooter
#> 135     16           1        3                                      was
#> 136     16           1        4                                described
#> 137     16           1        5                                       by
#> 138     16           1        6                                   police
#> 139     16           1        7                                       as
#> 140     16           1        8                                        a
#> 141     16           1        9                                    white
#> 142     16           1       10                                      man
#> 143     16           1       11                                        ,
#> 144     16           1       12                          approximately_6
#> 145     16           1       13                                       ft
#> 146     16           1       14                                        1
#> 147     16           1       15                                       in
#> 148     16           1       16                                        (
#> 149     16           1       17                                   185_cm
#> 150     16           1       18                                        )
#> 151     16           1       19                                     tall
#> 152     16           1       20                                        ,
#> 153     16           1       21                                  wearing
#> 154     16           1       22                                        a
#> 155     16           1       23                                    light
#> 156     16           1       24                                    brown
#> 157     16           1       25                                       or
#> 158     16           1       26                                    cream
#> 159     16           1       27                                        -
#> 160     16           1       28                                  colored
#> 161     16           1       29                                   hooded
#> 162     16           1       30                                   jacket
#> 163     16           1       31                                        ,
#> 164     16           1       32                                     dark
#> 165     16           1       33                                    pants
#> 166     16           1       34                                        ,
#> 167     16           1       35                                      and
#> 168     16           1       36                                    black
#> 169     16           1       37                                 sneakers
#> 170     16           1       38                                     with
#> 171     16           1       39                                    white
#> 172     16           1       40                                    soles
#> 173     16           1       41                                        .
#> 174     16           2        1                           31][39][57][58
#> 175     16           2        2                                        ]
#> 176     16           2        3                                   Police
#> 177     16           2        4                                     said
#> 178     16           2        5                                      the
#> 179     16           2        6                                  suspect
#> 180     16           2        7                                 appeared
#> 181     16           2        8                                       to
#> 182     16           2        9                                       be
#> 183     16           2       10                               proficient
#> 184     16           2       11                                       in
#> 185     16           2       12                                      the
#> 186     16           2       13                                      use
#> 187     16           2       14                                       of
#> 188     16           2       15                              firearms[30
#> 189     16           2       16                                        ]
#> 190     16           2       17                                      and
#> 191     16           2       18                                      was
#> 192     16           2       19                                described
#> 193     16           2       20                                       as
#> 194     16           2       21                                    being
#> 195     16           2       22                                        "
#> 196     16           2       23                                extremely
#> 197     16           2       24                                   camera
#> 198     16           2       25                                    savvy
#> 199     16           2       26                                        .
#> 200     16           2       27                                        "
#> 201     16           2        1                                        [
#> 202     18           1        1                                       69
#> 203     18           1        2                                        ]
#> 204     18           1        1                                 Mangione
#> 205     18           1        2                                       's
#> 206     18           1        3                                   mother
#> 207     18           1        4                                contacted
#> 208     18           1        5      the_San_Francisco_Police_Department
#> 209     18           1        6                                        ,
#> 210     18           1        7                                       as
#> 211     18           1        8                                      she
#> 212     18           1        9                                 believed
#> 213     18           1       10                                     that
#> 214     18           1       11                                 Mangione
#> 215     18           1       12                                    lived
#> 216     18           1       13                                       in
#> 217     18           1       14                            San_Francisco
#> 218     18           1       15                                      and
#> 219     18           1       16                                      had
#> 220     18           1       17                                        a
#> 221     18           1       18                                      job
#> 222     18           1       19                                       in
#> 223     18           1       20                                      the
#> 224     18           1       21                                     area
#> 225     18           1       22                                        .
#> 226     18           1        1                                        [
#> 227     19           1        1                                    Local
#> 228     19           1        2                                   police
#> 229     19           1        3                                       in
#> 230     19           1        4                                  Altoona
#> 231     19           1        5                                        ,
#> 232     19           1        6                             Pennsylvania
#> 233     19           1        7                                        ,
#> 234     19           1        8                                 arrested
#> 235     19           1        9                                 Mangione
#> 236     19           1       10                                       on
#> 237     19           1       11                        December_9_,_2024
#> 238     19           1       12                                        ,
#> 239     19           1       13                                       at
#> 240     19           1       14                                        a
#> 241     19           1       15                                 McDonald
#> 242     19           1       16                                       's
#> 243     19           1       17                               restaurant
#> 244     19           1       18                                       in
#> 245     19           1       19                                      the
#> 246     19           1       20                                     city
#> 247     19           1       21                                        .
#> 248     19           2        1                                       An
#> 249     19           2        2                                 employee
#> 250     19           2        3                                    there
#> 251     19           2        4                                   called
#> 252     19           2        5                                      the
#> 253     19           2        6                                   police
#> 254     19           2        7                                       to
#> 255     19           2        8                                      say
#> 256     19           2        9                                     that
#> 257     19           2       10                                        a
#> 258     19           2       11                                 customer
#> 259     19           2       12                               recognized
#> 260     19           2       13                                      the
#> 261     19           2       14                                  suspect
#> 262     19           2       15                                     from
#> 263     19           2       16                                   images
#> 264     19           2       17                                 released
#> 265     19           2       18                                       by
#> 266     19           2       19                                      the
#> 267     19           2       20                                     NYPD
#> 268     19           2       21                                        .
#> 269     19           2        1                                        [
#> 270     19           3        1                                       63
#> 271     19           3        2                                        ]
#> 272     19           3        1                                       In
#> 273     19           3        2                                      his
#> 274     19           3        3                                      bag
#> 275     19           3        4                                     they
#> 276     19           3        5                                    found
#> 277     19           3        6                                        a
#> 278     19           3        7                                       3D
#> 279     19           3        8                                        -
#> 280     19           3        9                                  printed
#> 281     19           3       10                                      gun
#> 282     19           3       11                                      and
#> 283     19           3       12                                        a
#> 284     19           3       13                                       3D
#> 285     19           3       14                                        -
#> 286     19           3       15                                  printed
#> 287     19           3       16                               suppressor
#> 288     19           3       17                                        ,
#> 289     19           3       18                                    which
#> 290     19           3       19                                      the
#> 291     19           3       20                                   police
#> 292     19           3       21                                    claim
#> 293     19           3       22                                      are
#> 294     19           3       23                               consistent
#> 295     19           3       24                                     with
#> 296     19           3       25                                      the
#> 297     19           3       26                                   weapon
#> 298     19           3       27                                     used
#> 299     19           3       28                                       in
#> 300     19           3       29                                      the
#> 301     19           3       30                                 shooting
#> 302     19           3       31                                        ,
#> 303     19           3       32                                      and
#> 304     19           3       33                                        a
#> 305     19           3       34                                falsified
#> 306     19           3       35                               New_Jersey
#> 307     19           3       36                                   driver
#> 308     19           3       37                                       's
#> 309     19           3       38                                  license
#> 310     19           3       39                                     with
#> 311     19           3       40                                      the
#> 312     19           3       41                                     same
#> 313     19           3       42                                     name
#> 314     19           3       43                                       as
#> 315     19           3       44                                      the
#> 316     19           3       45                                      one
#> 317     19           3       46                                     used
#> 318     19           3       47                                       by
#> 319     19           3       48                                      the
#> 320     19           3       49                                  alleged
#> 321     19           3       50                                  shooter
#> 322     19           3       51                                       to
#> 323     19           3       52                                    check
#> 324     19           3       53                                     into
#> 325     19           3       54                                      the
#> 326     19           3       55                                Manhattan
#> 327     19           3       56                                   hostel
#> 328     19           3       57                                        .
#> 329     19           3        1                                        [
#> 330     19           4        1                             8][73][3][74
#> 331     19           4        2                                        ]
#> 332     19           4        3                                         
#> 333     19           4        4                                      The
#> 334     19           4        5                                   police
#> 335     19           4        6                                     also
#> 336     19           4        7                                     said
#> 337     19           4        8                                     that
#> 338     19           4        9                                     when
#> 339     19           4       10                                     they
#> 340     19           4       11                                 arrested
#> 341     19           4       12                                 Mangione
#> 342     19           4       13                                        ,
#> 343     19           4       14                                     they
#> 344     19           4       15                                    found
#> 345     19           4       16                                        a
#> 346     19           4       17                       three_-_page,[74_]
#> 347     19           4       18                                      262
#> 348     19           4       19                                        -
#> 349     19           4       20                                     word
#> 350     19           4       21                              handwritten
#> 351     19           4       22                                 document
#> 352     19           4       23                                    about
#> 353     19           4       24                                      the
#> 354     19           4       25                                 American
#> 355     19           4       26                               healthcare
#> 356     19           4       27                                   system
#> 357     19           4       28                                        ,
#> 358     19           4       29                                    which
#> 359     19           4       30                                     they
#> 360     19           4       31                            characterized
#> 361     19           4       32                                       as
#> 362     19           4       33                                        a
#> 363     19           4       34                                manifesto
#> 364     19           4       35                                        .
#> 365     19           4        1                                        [
#> 366     23           1        1                                       85
#> 367     23           1        2                                        ]
#> 368     23           1        3                                   Police
#> 369     23           1        4                                  believe
#> 370     23           1        5                                      the
#> 371     23           1        6                                   motive
#> 372     23           1        7                                      was
#> 373     23           1        8                                  related
#> 374     23           1        9                                       to
#> 375     23           1       10                                       an
#> 376     23           1       11                                   injury
#> 377     23           1       12                                     that
#> 378     23           1       13                                 Mangione
#> 379     23           1       14                                      had
#> 380     23           1       15                                 suffered
#> 381     23           1       16                                     that
#> 382     23           1       17                                   caused
#> 383     23           1       18                                      him
#> 384     23           1       19                                       to
#> 385     23           1       20                                    visit
#> 386     23           1       21                                      the
#> 387     23           1       22                                emergency
#> 388     23           1       23                                     room
#> 389     23           1       24                                       in
#> 390     23           1       25                                July_2023
#> 391     23           1       26                                        .
#> 392     23           2        1                                 New_York
#> 393     23           2        2                                   Police
#> 394     23           2        3                                    Chief
#> 395     23           2        4                                       of
#> 396     23           2        5                               Detectives
#> 397     23           2        6                             Joseph_Kenny
#> 398     23           2        7                                 believes
#> 399     23           2        8                                 Mangione
#> 400     23           2        9                                      may
#> 401     23           2       10                                     have
#> 402     23           2       11                                 targeted
#> 403     23           2       12                                     them
#> 404     23           2       13                                  because
#> 405     23           2       14                                       of
#> 406     23           2       15                                      the
#> 407     23           2       16                                  company
#> 408     23           2       17                                       's
#> 409     23           2       18                                     size
#> 410     23           2       19                                        .
#> 411     23           2        1                                        [
#> 412     24           1        1                                   Police
#> 413     24           1        2                                  believe
#> 414     24           1        3                                     that
#> 415     24           1        4                                 Mangione
#> 416     24           1        5                                      was
#> 417     24           1        6                                 inspired
#> 418     24           1        7                                       by
#> 419     24           1        8                         Ted_Kaczynski_'s
#> 420     24           1        9        Industrial_Society_and_Its_Future
#> 421     24           1       10                                        .
#> 422     24           1        1                                        [
#>                                        lemma    pos entity_type
#> 1                                         11 ENTITY    CARDINAL
#> 2                                          ]  PUNCT            
#> 3                                   mangione   NOUN            
#> 4                                         be    AUX            
#> 5                                       hold   VERB            
#> 6                                    without    ADP            
#> 7                                       bail   NOUN            
#> 8                                         in    ADP            
#> 9                               Pennsylvania ENTITY         GPE
#> 10                                        on    ADP            
#> 11                                    charge   NOUN            
#> 12                                        of    ADP            
#> 13                                possession   NOUN            
#> 14                                        of    ADP            
#> 15                                        an    DET            
#> 16                                unlicensed    ADJ            
#> 17                                   firearm   NOUN            
#> 18                                         ,  PUNCT            
#> 19                                   forgery   NOUN            
#> 20                                         ,  PUNCT            
#> 21                                       and  CCONJ            
#> 22                                   provide   VERB            
#> 23                                     false    ADJ            
#> 24                                New_Jersey ENTITY         GPE
#> 25                                         -  PUNCT            
#> 26                                  resident   NOUN            
#> 27                            identification   NOUN            
#> 28                                        to    ADP            
#> 29                                    police   NOUN            
#> 30                                         .  PUNCT            
#> 31                                         [      X            
#> 32                                        12 ENTITY    CARDINAL
#> 33                                         ]  PUNCT            
#> 34                                    Police   NOUN            
#> 35                                   believe   VERB            
#> 36                                      that  SCONJ            
#> 37                                        he   PRON            
#> 38                                        be    AUX            
#> 39                                   inspire   VERB            
#> 40                                        by    ADP            
#> 41                          Ted_Kaczynski_'s ENTITY      PERSON
#> 42                                     essay    ADJ            
#> 43         Industrial_Society_and_its_future ENTITY         ORG
#> 44                                         (  PUNCT            
#> 45                                      1995 ENTITY        DATE
#> 46                                         )  PUNCT            
#> 47                                         ,  PUNCT            
#> 48                                       and  CCONJ            
#> 49                                  motivate   VERB            
#> 50                                        by    ADP            
#> 51                                       his   PRON            
#> 52                                  personal    ADJ            
#> 53                                      view   NOUN            
#> 54                                        on    ADP            
#> 55                                    health   NOUN            
#> 56                                 insurance   NOUN            
#> 57                                         .  PUNCT            
#> 58                                         [      X            
#> 59                                        39 ENTITY    CARDINAL
#> 60                                         ]  PUNCT            
#> 61                                    accord   VERB            
#> 62                                        to    ADP            
#> 63                                       the    DET            
#> 64                                    police   NOUN            
#> 65                                         ,  PUNCT            
#> 66                                        he   PRON            
#> 67                                      then    ADV            
#> 68                                     leave   VERB            
#> 69                                       the    DET            
#> 70                                      city   NOUN            
#> 71                                      from    ADP            
#> 72  the_George_Washington_Bridge_Bus_Station ENTITY         ORG
#> 73                                       far    ADV            
#> 74                                    uptown   VERB            
#> 75                                        in    ADP            
#> 76                           Upper_Manhattan ENTITY         LOC
#> 77                                         .  PUNCT            
#> 78                                         [      X            
#> 79                                        49 ENTITY    CARDINAL
#> 80                                         ]  PUNCT            
#> 81                               accordingly    ADV            
#> 82                                         ,  PUNCT            
#> 83                                    police   NOUN            
#> 84                                     state   VERB            
#> 85                                      they   PRON            
#> 86                                        be    AUX            
#> 87                               investigate   VERB            
#> 88                                   whether  SCONJ            
#> 89                                       the    DET            
#> 90                                      word   NOUN            
#> 91                                   suggest   VERB            
#> 92                                       the    DET            
#> 93                                    killer   NOUN            
#> 94                                        's   PART            
#> 95                                    motive   NOUN            
#> 96                                         .  PUNCT            
#> 97                                         [      X            
#> 98                                        50 ENTITY    CARDINAL
#> 99                                         ]  PUNCT            
#> 100                                   Police   NOUN            
#> 101                                      say   VERB            
#> 102                                     they   PRON            
#> 103                                  believe   VERB            
#> 104                                     they   PRON            
#> 105                                     find   VERB            
#> 106                                      the    DET            
#> 107                                  shooter   NOUN            
#> 108                                       's   PART            
#> 109                                 backpack   NOUN            
#> 110                                       in    ADP            
#> 111                             Central_Park ENTITY         LOC
#> 112                                       on    ADP            
#> 113                        December_6_,_2024 ENTITY        DATE
#> 114                                        .  PUNCT            
#> 115                                        [      X            
#> 116                                      the    DET            
#> 117                            New_York_City ENTITY         GPE
#> 118                                   Police  PROPN            
#> 119                               Department  PROPN            
#> 120                                    offer   VERB            
#> 121                                        a    DET            
#> 122                                   reward   NOUN            
#> 123                           up_to_$_10,000 ENTITY       MONEY
#> 124                                      for    ADP            
#> 125                              information   NOUN            
#> 126                                    about    ADP            
#> 127                                      the    DET            
#> 128                                  shooter   NOUN            
#> 129                                       on    ADP            
#> 130                        December_4_,_2024 ENTITY        DATE
#> 131                                        .  PUNCT            
#> 132                                        [      X            
#> 133                                      the    DET            
#> 134                                  shooter   NOUN            
#> 135                                       be    AUX            
#> 136                                 describe   VERB            
#> 137                                       by    ADP            
#> 138                                   police   NOUN            
#> 139                                       as    ADP            
#> 140                                        a    DET            
#> 141                                    white    ADJ            
#> 142                                      man   NOUN            
#> 143                                        ,  PUNCT            
#> 144                          approximately_6 ENTITY    CARDINAL
#> 145                                       ft   NOUN            
#> 146                                        1    NUM            
#> 147                                       in    ADP            
#> 148                                        (  PUNCT            
#> 149                                   185_cm ENTITY    QUANTITY
#> 150                                        )  PUNCT            
#> 151                                     tall    ADJ            
#> 152                                        ,  PUNCT            
#> 153                                     wear   VERB            
#> 154                                        a    DET            
#> 155                                    light    ADJ            
#> 156                                    brown    ADJ            
#> 157                                       or  CCONJ            
#> 158                                    cream   NOUN            
#> 159                                        -  PUNCT            
#> 160                                    color   VERB            
#> 161                                   hooded    ADJ            
#> 162                                   jacket   NOUN            
#> 163                                        ,  PUNCT            
#> 164                                     dark    ADJ            
#> 165                                     pant   NOUN            
#> 166                                        ,  PUNCT            
#> 167                                      and  CCONJ            
#> 168                                    black    ADJ            
#> 169                                  sneaker   NOUN            
#> 170                                     with    ADP            
#> 171                                    white    ADJ            
#> 172                                      sol   NOUN            
#> 173                                        .  PUNCT            
#> 174                           31][39][57][58 ENTITY    CARDINAL
#> 175                                        ]  PUNCT            
#> 176                                   Police   NOUN            
#> 177                                      say   VERB            
#> 178                                      the    DET            
#> 179                                  suspect   NOUN            
#> 180                                   appear   VERB            
#> 181                                       to   PART            
#> 182                                       be    AUX            
#> 183                               proficient    ADJ            
#> 184                                       in    ADP            
#> 185                                      the    DET            
#> 186                                      use   NOUN            
#> 187                                       of    ADP            
#> 188                              firearms[30   NOUN            
#> 189                                        ]  PUNCT            
#> 190                                      and  CCONJ            
#> 191                                       be    AUX            
#> 192                                 describe   VERB            
#> 193                                       as    ADP            
#> 194                                       be    AUX            
#> 195                                        "  PUNCT            
#> 196                                extremely    ADV            
#> 197                                   camera   NOUN            
#> 198                                    savvy   NOUN            
#> 199                                        .  PUNCT            
#> 200                                        "  PUNCT            
#> 201                                        [      X            
#> 202                                       69 ENTITY    CARDINAL
#> 203                                        ]  PUNCT            
#> 204                                 Mangione ENTITY         ORG
#> 205                                       's   PART            
#> 206                                   mother   NOUN            
#> 207                                  contact   VERB            
#> 208      the_San_Francisco_Police_Department ENTITY         ORG
#> 209                                        ,  PUNCT            
#> 210                                       as  SCONJ            
#> 211                                      she   PRON            
#> 212                                  believe   VERB            
#> 213                                     that  SCONJ            
#> 214                                 Mangione ENTITY         ORG
#> 215                                     live   VERB            
#> 216                                       in    ADP            
#> 217                            San_Francisco ENTITY         GPE
#> 218                                      and  CCONJ            
#> 219                                     have   VERB            
#> 220                                        a    DET            
#> 221                                      job   NOUN            
#> 222                                       in    ADP            
#> 223                                      the    DET            
#> 224                                     area   NOUN            
#> 225                                        .  PUNCT            
#> 226                                        [      X            
#> 227                                    local    ADJ            
#> 228                                   police   NOUN            
#> 229                                       in    ADP            
#> 230                                  Altoona ENTITY         GPE
#> 231                                        ,  PUNCT            
#> 232                             Pennsylvania ENTITY         GPE
#> 233                                        ,  PUNCT            
#> 234                                   arrest   VERB            
#> 235                                 Mangione ENTITY         ORG
#> 236                                       on    ADP            
#> 237                        December_9_,_2024 ENTITY        DATE
#> 238                                        ,  PUNCT            
#> 239                                       at    ADP            
#> 240                                        a    DET            
#> 241                                 McDonald ENTITY         ORG
#> 242                                       's   PART            
#> 243                               restaurant   NOUN            
#> 244                                       in    ADP            
#> 245                                      the    DET            
#> 246                                     city   NOUN            
#> 247                                        .  PUNCT            
#> 248                                       an    DET            
#> 249                                 employee   NOUN            
#> 250                                    there    ADV            
#> 251                                     call   VERB            
#> 252                                      the    DET            
#> 253                                   police   NOUN            
#> 254                                       to   PART            
#> 255                                      say   VERB            
#> 256                                     that  SCONJ            
#> 257                                        a    DET            
#> 258                                 customer   NOUN            
#> 259                                recognize   VERB            
#> 260                                      the    DET            
#> 261                                  suspect   NOUN            
#> 262                                     from    ADP            
#> 263                                    image   NOUN            
#> 264                                  release   VERB            
#> 265                                       by    ADP            
#> 266                                      the    DET            
#> 267                                     NYPD ENTITY         ORG
#> 268                                        .  PUNCT            
#> 269                                        [      X            
#> 270                                       63 ENTITY    CARDINAL
#> 271                                        ]  PUNCT            
#> 272                                       in    ADP            
#> 273                                      his   PRON            
#> 274                                      bag   NOUN            
#> 275                                     they   PRON            
#> 276                                     find   VERB            
#> 277                                        a    DET            
#> 278                                       3d   NOUN            
#> 279                                        -  PUNCT            
#> 280                                    print   VERB            
#> 281                                      gun   NOUN            
#> 282                                      and  CCONJ            
#> 283                                        a    DET            
#> 284                                       3d   NOUN            
#> 285                                        -  PUNCT            
#> 286                                    print   VERB            
#> 287                               suppressor   NOUN            
#> 288                                        ,  PUNCT            
#> 289                                    which   PRON            
#> 290                                      the    DET            
#> 291                                   police   NOUN            
#> 292                                    claim   NOUN            
#> 293                                       be    AUX            
#> 294                               consistent    ADJ            
#> 295                                     with    ADP            
#> 296                                      the    DET            
#> 297                                   weapon   NOUN            
#> 298                                      use   VERB            
#> 299                                       in    ADP            
#> 300                                      the    DET            
#> 301                                 shooting   NOUN            
#> 302                                        ,  PUNCT            
#> 303                                      and  CCONJ            
#> 304                                        a    DET            
#> 305                                  falsify   VERB            
#> 306                               New_Jersey ENTITY         GPE
#> 307                                   driver   NOUN            
#> 308                                       's   PART            
#> 309                                  license   NOUN            
#> 310                                     with    ADP            
#> 311                                      the    DET            
#> 312                                     same    ADJ            
#> 313                                     name   NOUN            
#> 314                                       as    ADP            
#> 315                                      the    DET            
#> 316                                      one   NOUN            
#> 317                                      use   VERB            
#> 318                                       by    ADP            
#> 319                                      the    DET            
#> 320                                  alleged    ADJ            
#> 321                                  shooter   NOUN            
#> 322                                       to   PART            
#> 323                                    check   VERB            
#> 324                                     into    ADP            
#> 325                                      the    DET            
#> 326                                Manhattan ENTITY         GPE
#> 327                                   hostel   NOUN            
#> 328                                        .  PUNCT            
#> 329                                        [      X            
#> 330                             8][73][3][74 ENTITY    CARDINAL
#> 331                                        ]  PUNCT            
#> 332                                           SPACE            
#> 333                                      the    DET            
#> 334                                   police   NOUN            
#> 335                                     also    ADV            
#> 336                                      say   VERB            
#> 337                                     that  SCONJ            
#> 338                                     when  SCONJ            
#> 339                                     they   PRON            
#> 340                                   arrest   VERB            
#> 341                                 Mangione  PROPN            
#> 342                                        ,  PUNCT            
#> 343                                     they   PRON            
#> 344                                     find   VERB            
#> 345                                        a    DET            
#> 346                       three_-_page,[74_] ENTITY    CARDINAL
#> 347                                      262 ENTITY    CARDINAL
#> 348                                        -  PUNCT            
#> 349                                     word   NOUN            
#> 350                              handwritten    ADJ            
#> 351                                 document   NOUN            
#> 352                                    about    ADP            
#> 353                                      the    DET            
#> 354                                 american ENTITY        NORP
#> 355                               healthcare   NOUN            
#> 356                                   system   NOUN            
#> 357                                        ,  PUNCT            
#> 358                                    which   PRON            
#> 359                                     they   PRON            
#> 360                             characterize   VERB            
#> 361                                       as    ADP            
#> 362                                        a    DET            
#> 363                                manifesto   NOUN            
#> 364                                        .  PUNCT            
#> 365                                        [      X            
#> 366                                       85 ENTITY    CARDINAL
#> 367                                        ]  PUNCT            
#> 368                                   Police   NOUN            
#> 369                                  believe   VERB            
#> 370                                      the    DET            
#> 371                                   motive   NOUN            
#> 372                                       be    AUX            
#> 373                                   relate   VERB            
#> 374                                       to    ADP            
#> 375                                       an    DET            
#> 376                                   injury   NOUN            
#> 377                                     that   PRON            
#> 378                                 Mangione ENTITY         ORG
#> 379                                     have    AUX            
#> 380                                   suffer   VERB            
#> 381                                     that   PRON            
#> 382                                    cause   VERB            
#> 383                                       he   PRON            
#> 384                                       to   PART            
#> 385                                    visit   VERB            
#> 386                                      the    DET            
#> 387                                emergency   NOUN            
#> 388                                     room   NOUN            
#> 389                                       in    ADP            
#> 390                                July_2023 ENTITY        DATE
#> 391                                        .  PUNCT            
#> 392                                 New_York ENTITY         GPE
#> 393                                   Police  PROPN            
#> 394                                    Chief  PROPN            
#> 395                                       of    ADP            
#> 396                               Detectives  PROPN            
#> 397                             Joseph_Kenny ENTITY      PERSON
#> 398                                  believe   VERB            
#> 399                                 Mangione  PROPN            
#> 400                                      may    AUX            
#> 401                                     have    AUX            
#> 402                                   target   VERB            
#> 403                                     they   PRON            
#> 404                                  because  SCONJ            
#> 405                                       of    ADP            
#> 406                                      the    DET            
#> 407                                  company   NOUN            
#> 408                                       's   PART            
#> 409                                     size   NOUN            
#> 410                                        .  PUNCT            
#> 411                                        [      X            
#> 412                                   Police   NOUN            
#> 413                                  believe   VERB            
#> 414                                     that  SCONJ            
#> 415                                 Mangione ENTITY         ORG
#> 416                                       be    AUX            
#> 417                                  inspire   VERB            
#> 418                                       by    ADP            
#> 419                         Ted_Kaczynski_'s ENTITY      PERSON
#> 420        Industrial_Society_and_its_Future ENTITY         ORG
#> 421                                        .  PUNCT            
#> 422                                        [      X