chore: mise à jour output pipeline (anonymized + structured)

Résultats de re-traitement pipeline v2 sur 261 dossiers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-03-07 23:14:42 +01:00
parent c73515ac89
commit 13fe9fa666
734 changed files with 157158 additions and 304963 deletions

View File

@@ -0,0 +1,33 @@
{
"source_file": "CRO-23096332.pdf",
"total_replacements": 12,
"regex_replacements": 5,
"ner_replacements": 4,
"sweep_replacements": 3,
"entities_found": [
{
"original": "BERNACHOT-FAURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9899211525917053
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9945400953292847
},
{
"original": "CHRISTIAN",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.967853307723999
},
{
"original": "BERNACHOT-FAURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9965351223945618
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "CRO 23096332.pdf",
"total_replacements": 12,
"regex_replacements": 5,
"ner_replacements": 4,
"sweep_replacements": 3,
"entities_found": [
{
"original": "BERNACHOT-FAURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9899211525917053
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9945400953292847
},
{
"original": "CHRISTIAN",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.967853307723999
},
{
"original": "BERNACHOT-FAURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9965351223945618
}
]
}

View File

@@ -0,0 +1,891 @@
{
"source_file": "trackare-23011489-23096332_23011489_23096332.pdf",
"total_replacements": 1081,
"regex_replacements": 258,
"ner_replacements": 94,
"sweep_replacements": 729,
"entities_found": [
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23011489",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096332",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "Nationalité: FRANCE Code Postal: 64100",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "11 AVENUE DE ROSSI Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Paul Jean Flagyl",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8647840619087219
},
{
"original": "Claforan",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8333049416542053
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8489370346069336
},
{
"original": "BURTIN BURTIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9922988414764404
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9650837182998657
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9550626873970032
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9900617003440857
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9410816431045532
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9886078834533691
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8020169138908386
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9825113415718079
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9935013055801392
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.974027693271637
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9611510634422302
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9409450888633728
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8945591449737549
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8838852047920227
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8844579458236694
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9937558770179749
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9962358474731445
},
{
"original": "MG KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8322917819023132
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8757144808769226
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.994924783706665
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.9934707283973694
},
{
"original": "Admin",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.92433100938797
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9646549224853516
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9817743301391602
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9924170970916748
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.93660569190979
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9401805996894836
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.992927074432373
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8997429013252258
},
{
"original": "NARZABAL Julie Réalisé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8297316431999207
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9675109386444092
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9198686480522156
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9770469069480896
},
{
"original": "LARRIEU-",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8036184310913086
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9356527924537659
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9937999248504639
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9921578764915466
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9943418502807617
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9929172396659851
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9956858158111572
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9885463714599609
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9959114193916321
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9943342208862305
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9637172818183899
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9421079158782959
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9504805207252502
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9024047255516052
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9783715605735779
},
{
"original": "LARRIEU",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9633989334106445
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9554091095924377
},
{
"original": "LARRIEU-",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8119601011276245
},
{
"original": "MG KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8863533139228821
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.922724723815918
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.8655591607093811
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.947304904460907
},
{
"original": "OXYNORMORO 5MG C",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8800508379936218
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8492390513420105
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9485771059989929
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_7]",
"source": "ner",
"score": 0.8307890892028809
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9843466877937317
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9847761988639832
},
{
"original": "NARZABAL Julie POC",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9605070948600769
},
{
"original": "NARZABAL Julie POC",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9237445592880249
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9777634739875793
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9203883409500122
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8797113299369812
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.917142391204834
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9318748712539673
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9452023506164551
},
{
"original": "Paul Jean Réalisé",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8163549900054932
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9657363295555115
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9208517074584961
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9553509950637817
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9641865491867065
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9455852508544922
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9522570371627808
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.917205810546875
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.845329225063324
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.939300537109375
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9988054037094116
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9987215399742126
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9990615248680115
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9989731907844543
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9989143013954163
},
{
"original": "Paul Jean MATERNOWSKI",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9990882873535156
},
{
"original": "Bochra ZAYENE",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9450609087944031
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9338946342468262
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9794166684150696
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9640618562698364
},
{
"original": "MATERNOWSKI",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9867444038391113
},
{
"original": "Paul Jean",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9611458778381348
}
]
}