{
 "source": "Imperial Careers data/volume/col*/bios.jsonl; parser col_match/services/rules_parse.py",
 "note": "parser = rules: accepted by the rule-based parser; qwen: refused by the rules (flag rules_failed) and read by Qwen. Accepted output is not necessarily correct.",
 "totals": {
  "editions": 66,
  "biographies_read": 202100,
  "rules": 157108,
  "qwen": 44578,
  "unparsed": 414,
  "not_a_bio": 6351,
  "rules_share": 0.777
 },
 "editions": {
  "col1867": {
   "rules": 907,
   "qwen": 447,
   "unparsed": 22,
   "rules_share": 0.659
  },
  "col1877": {
   "rules": 754,
   "qwen": 496,
   "unparsed": 14,
   "rules_share": 0.597
  },
  "col1878": {
   "rules": 772,
   "qwen": 570,
   "unparsed": 16,
   "rules_share": 0.568
  },
  "col1879": {
   "rules": 794,
   "qwen": 630,
   "unparsed": 15,
   "rules_share": 0.552
  },
  "col1880": {
   "rules": 789,
   "qwen": 607,
   "unparsed": 10,
   "rules_share": 0.561
  },
  "col1883": {
   "rules": 837,
   "qwen": 679,
   "unparsed": 122,
   "rules_share": 0.511
  },
  "col1886": {
   "rules": 1143,
   "qwen": 721,
   "unparsed": 26,
   "rules_share": 0.605
  },
  "col1888": {
   "rules": 1333,
   "qwen": 820,
   "unparsed": 27,
   "rules_share": 0.611
  },
  "col1889": {
   "rules": 1387,
   "qwen": 841,
   "unparsed": 16,
   "rules_share": 0.618
  },
  "col1890": {
   "rules": 1467,
   "qwen": 825,
   "unparsed": 24,
   "rules_share": 0.633
  },
  "col1894": {
   "rules": 1342,
   "qwen": 795,
   "unparsed": 10,
   "rules_share": 0.625
  },
  "col1896": {
   "rules": 1318,
   "qwen": 816,
   "unparsed": 9,
   "rules_share": 0.615
  },
  "col1897": {
   "rules": 1255,
   "qwen": 754,
   "unparsed": 9,
   "rules_share": 0.622
  },
  "col1898": {
   "rules": 1364,
   "qwen": 762,
   "unparsed": 13,
   "rules_share": 0.638
  },
  "col1899": {
   "rules": 1291,
   "qwen": 774,
   "unparsed": 9,
   "rules_share": 0.622
  },
  "col1900": {
   "rules": 1252,
   "qwen": 761,
   "unparsed": 7,
   "rules_share": 0.62
  },
  "col1905": {
   "rules": 1416,
   "qwen": 832,
   "unparsed": 2,
   "rules_share": 0.629
  },
  "col1906": {
   "rules": 1424,
   "qwen": 868,
   "unparsed": 2,
   "rules_share": 0.621
  },
  "col1907": {
   "rules": 1421,
   "qwen": 871,
   "unparsed": 2,
   "rules_share": 0.619
  },
  "col1908": {
   "rules": 1520,
   "qwen": 961,
   "unparsed": 2,
   "rules_share": 0.612
  },
  "col1909": {
   "rules": 1966,
   "qwen": 1214,
   "unparsed": 2,
   "rules_share": 0.618
  },
  "col1910": {
   "rules": 1738,
   "qwen": 984,
   "unparsed": 2,
   "rules_share": 0.638
  },
  "col1911": {
   "rules": 1890,
   "qwen": 1017,
   "unparsed": 2,
   "rules_share": 0.65
  },
  "col1912": {
   "rules": 1929,
   "qwen": 1054,
   "unparsed": 2,
   "rules_share": 0.646
  },
  "col1913": {
   "rules": 2032,
   "qwen": 1096,
   "unparsed": 1,
   "rules_share": 0.649
  },
  "col1914": {
   "rules": 2116,
   "qwen": 1104,
   "unparsed": 1,
   "rules_share": 0.657
  },
  "col1915": {
   "rules": 2175,
   "qwen": 1061,
   "unparsed": 2,
   "rules_share": 0.672
  },
  "col1917": {
   "rules": 2284,
   "qwen": 1014,
   "unparsed": 1,
   "rules_share": 0.692
  },
  "col1918": {
   "rules": 2316,
   "qwen": 1034,
   "unparsed": 1,
   "rules_share": 0.691
  },
  "col1919": {
   "rules": 2245,
   "qwen": 1028,
   "unparsed": 1,
   "rules_share": 0.686
  },
  "col1920": {
   "rules": 2286,
   "qwen": 1035,
   "unparsed": 1,
   "rules_share": 0.688
  },
  "col1921": {
   "rules": 2384,
   "qwen": 1032,
   "unparsed": 1,
   "rules_share": 0.698
  },
  "col1922": {
   "rules": 2461,
   "qwen": 995,
   "unparsed": 1,
   "rules_share": 0.712
  },
  "col1923": {
   "rules": 2479,
   "qwen": 954,
   "unparsed": 0,
   "rules_share": 0.722
  },
  "col1924": {
   "rules": 2469,
   "qwen": 936,
   "unparsed": 0,
   "rules_share": 0.725
  },
  "col1925": {
   "rules": 2426,
   "qwen": 884,
   "unparsed": 4,
   "rules_share": 0.732
  },
  "col1927": {
   "rules": 2617,
   "qwen": 901,
   "unparsed": 0,
   "rules_share": 0.744
  },
  "col1928": {
   "rules": 2729,
   "qwen": 944,
   "unparsed": 0,
   "rules_share": 0.743
  },
  "col1929": {
   "rules": 2654,
   "qwen": 860,
   "unparsed": 1,
   "rules_share": 0.755
  },
  "col1930": {
   "rules": 2594,
   "qwen": 860,
   "unparsed": 0,
   "rules_share": 0.751
  },
  "col1931": {
   "rules": 2698,
   "qwen": 889,
   "unparsed": 0,
   "rules_share": 0.752
  },
  "col1932": {
   "rules": 2784,
   "qwen": 827,
   "unparsed": 1,
   "rules_share": 0.771
  },
  "col1933": {
   "rules": 2737,
   "qwen": 778,
   "unparsed": 0,
   "rules_share": 0.779
  },
  "col1934": {
   "rules": 2642,
   "qwen": 743,
   "unparsed": 0,
   "rules_share": 0.781
  },
  "col1936": {
   "rules": 2833,
   "qwen": 771,
   "unparsed": 1,
   "rules_share": 0.786
  },
  "col1937": {
   "rules": 2619,
   "qwen": 715,
   "unparsed": 1,
   "rules_share": 0.785
  },
  "col1939": {
   "rules": 2999,
   "qwen": 755,
   "unparsed": 2,
   "rules_share": 0.798
  },
  "col1940": {
   "rules": 3098,
   "qwen": 778,
   "unparsed": 1,
   "rules_share": 0.799
  },
  "col1948": {
   "rules": 2914,
   "qwen": 304,
   "unparsed": 19,
   "rules_share": 0.9
  },
  "col1949": {
   "rules": 3247,
   "qwen": 295,
   "unparsed": 0,
   "rules_share": 0.917
  },
  "col1950": {
   "rules": 3702,
   "qwen": 297,
   "unparsed": 0,
   "rules_share": 0.926
  },
  "col1951": {
   "rules": 4031,
   "qwen": 309,
   "unparsed": 0,
   "rules_share": 0.929
  },
  "col1953": {
   "rules": 1632,
   "qwen": 114,
   "unparsed": 0,
   "rules_share": 0.935
  },
  "col1954": {
   "rules": 1784,
   "qwen": 125,
   "unparsed": 0,
   "rules_share": 0.935
  },
  "col1955": {
   "rules": 1927,
   "qwen": 146,
   "unparsed": 0,
   "rules_share": 0.93
  },
  "col1956": {
   "rules": 2821,
   "qwen": 183,
   "unparsed": 0,
   "rules_share": 0.939
  },
  "col1957": {
   "rules": 3926,
   "qwen": 211,
   "unparsed": 2,
   "rules_share": 0.949
  },
  "col1958": {
   "rules": 4087,
   "qwen": 201,
   "unparsed": 2,
   "rules_share": 0.953
  },
  "col1959": {
   "rules": 4619,
   "qwen": 210,
   "unparsed": 2,
   "rules_share": 0.956
  },
  "col1960": {
   "rules": 4747,
   "qwen": 201,
   "unparsed": 2,
   "rules_share": 0.959
  },
  "col1961": {
   "rules": 4833,
   "qwen": 211,
   "unparsed": 1,
   "rules_share": 0.958
  },
  "col1962": {
   "rules": 4895,
   "qwen": 143,
   "unparsed": 0,
   "rules_share": 0.972
  },
  "col1963": {
   "rules": 4881,
   "qwen": 147,
   "unparsed": 0,
   "rules_share": 0.971
  },
  "col1964": {
   "rules": 4430,
   "qwen": 133,
   "unparsed": 0,
   "rules_share": 0.971
  },
  "col1965": {
   "rules": 3569,
   "qwen": 129,
   "unparsed": 0,
   "rules_share": 0.965
  },
  "col1966": {
   "rules": 3077,
   "qwen": 126,
   "unparsed": 0,
   "rules_share": 0.961
  }
 },
 "examples": [
  {
   "edition": "col1936",
   "bio_id": "col1936-p832b11",
   "parser": "rules",
   "flags": [
    "place_inherited:2"
   ],
   "raw_text": "BALMER, F. E.—Dep. chief acctnt., G.P.O., E. Africa Prot., Mar., 1919; ch. acctnt., G.P.O., Kenya, Oct., 1919; ch. acctnt., Kenya-Uganda-Tanganyika post and tel. service, 1933; senr. dep. P.M.G., do., 1935.",
   "events": [
    {
     "position": "Dep. chief acctnt., G.P.O.",
     "place": "East Africa",
     "year_start": 1919,
     "year_end": null
    },
    {
     "position": "ch. acctnt., G.P.O.",
     "place": "Kenya",
     "year_start": 1919,
     "year_end": null
    },
    {
     "position": "ch. acctnt., Kenya-Uganda-Tanganyika post and tel. service",
     "place": "Kenya",
     "year_start": 1933,
     "year_end": null
    },
    {
     "position": "senr. dep. P.M.G.",
     "place": "Dominions Office",
     "year_start": 1935,
     "year_end": null
    }
   ]
  },
  {
   "edition": "col1940",
   "bio_id": "col1940-p905b22",
   "parser": "rules",
   "flags": [
    "place_inherited:1",
    "place_inherited:2",
    "place_inherited:3",
    "place_inherited:4",
    "place_inherited:5",
    "place_inherited:6"
   ],
   "raw_text": "CONNOLLY, HON. SIR JAMES DANIEL, KT. BACH. (1920). —B. 1870; ed. Warwick Pub. Schl. and Catholic Schl.; M.L.C., Western Australia, 1902; col. sec. and min. of com. and lab., 1906; col. sec. and min. of pub. health, 1910; leader of leg. coun. from 1906 to 1911; M.L.A. for Perth, 1914; agt. genl. in London for Western Australia, 1917-23; agt. gen. in London for Malta, 1930.",
   "events": [
    {
     "position": "M.L.C.",
     "place": "Western Australia",
     "year_start": 1902,
     "year_end": null
    },
    {
     "position": "col. sec. and min. of com. and lab",
     "place": "Western Australia",
     "year_start": 1906,
     "year_end": null
    },
    {
     "position": "col. sec. and min. of pub. health",
     "place": "Western Australia",
     "year_start": 1910,
     "year_end": null
    },
    {
     "position": "leader of leg. coun. from",
     "place": "Western Australia",
     "year_start": 1906,
     "year_end": 1911
    },
    {
     "position": "M.L.A. for Perth",
     "place": "Western Australia",
     "year_start": 1914,
     "year_end": null
    },
    {
     "position": "agt. genl. in London for Western Australia",
     "place": "Western Australia",
     "year_start": 1917,
     "year_end": 1923
    },
    {
     "position": "agt. gen. in London for Malta",
     "place": "Western Australia",
     "year_start": 1930,
     "year_end": null
    }
   ]
  },
  {
   "edition": "col1867",
   "bio_id": "col1867-p271b15",
   "parser": "qwen",
   "flags": [
    "rules_failed"
   ],
   "raw_text": "WODEHOUSE, SIR PHILIP E., K.C.B. (Creat. 1862.)—Entered the Ceylon civil service as a writer, May, 1828; promoted to be assistant colonial secretary and clerk of the executive and legislative councils, Oct. 1833; district judge of Kandy, 1840; government agent for the western province, 1843; was appointed superintendent of Honduras, 1851; in Feb. 1854, governor of British Guiana; was employed in 1858 on a special mission to the government of Venezuela; and in 1861 was appointed governor of the Cape of Good Hope; is also high commissioner in South Africa.",
   "events": [
    {
     "position": "writer",
     "place": "Ceylon",
     "year_start": 1828,
     "year_end": null
    },
    {
     "position": "assistant colonial secretary and clerk of the executive and legislative councils",
     "place": "Ceylon",
     "year_start": 1833,
     "year_end": null
    },
    {
     "position": "district judge",
     "place": "Kandy",
     "year_start": 1840,
     "year_end": null
    },
    {
     "position": "government agent for the western province",
     "place": "Ceylon",
     "year_start": 1843,
     "year_end": null
    },
    {
     "position": "superintendent",
     "place": "Honduras",
     "year_start": 1851,
     "year_end": null
    },
    {
     "position": "governor",
     "place": "British Guiana",
     "year_start": 1854,
     "year_end": null
    },
    {
     "position": "special mission",
     "place": "Venezuela",
     "year_start": 1858,
     "year_end": null
    },
    {
     "position": "governor",
     "place": "Cape of Good Hope",
     "year_start": 1861,
     "year_end": null
    },
    {
     "position": "high commissioner in South Africa",
     "place": "Cape of Good Hope",
     "year_start": null,
     "year_end": null
    }
   ]
  }
 ]
}
