glam/reports/entity_extraction_stats.md
2025-12-14 17:09:55 +01:00

15 KiB

Entity Extraction Statistics Report

Generated: 2025-12-13 18:49:19

Summary

Metric Value
Total custodian files scanned 1,865
Files with validated_entity_claims 1,291 (69.2%)
Total entities extracted 11,723
Unique entity names 9,538
Entities appearing in multiple files 1,210
Average confidence score 0.954
Unique entity types 135

Entity Types Breakdown

Type Label Count %
APP.URL URL/Website 2,810 24.0%
GRP.HER Heritage institution 1,383 11.8%
TOP.SET Settlement/City 1,187 10.1%
TMP.DAB Date (absolute) 636 5.4%
TOP.ADR Address 368 3.1%
APP.TIT Title (document) 338 2.9%
AGT.PER Person 324 2.8%
GRP.ASS Association/Society 322 2.7%
GRP.GOV Government body 278 2.4%
APP.TTL Title (general) 253 2.2%
WRK.WEB Website/Web resource 251 2.1%
THG.CON Contact info 239 2.0%
APP.EXH Exhibition name 237 2.0%
TOP.REG Region/Province 223 1.9%
TMP.OPH Opening hours 198 1.7%
TOP.CTY Country 160 1.4%
THG.LNG Language 154 1.3%
GRP.COR Corporation 137 1.2%
TOP.BLD Building 137 1.2%
THG.ART Artifact/Object 121 1.0%
WRK.COL Collection (as work) 117 1.0%
THG.EVT Event 113 1.0%
WRK.TXT Text/Document 90 0.8%
QTY.CNT Count/Number 80 0.7%
THG.PHO Photograph 77 0.7%
APP.COL Collection name 65 0.6%
GRP.EDU Educational institution 64 0.5%
TMP.DRL Date range/Duration 58 0.5%
QTY.CUR Currency/Price 57 0.5%
ROL.POS ROL.POS 56 0.5%
GRP.UNT GRP.UNT 56 0.5%
THG.DOC THG.DOC 53 0.5%
WRK.URL WRK.URL 52 0.4%
TMP.TAB TMP.TAB 52 0.4%
TMP.RNG TMP.RNG 50 0.4%
WRK.VIS WRK.VIS 49 0.4%
TMP.EXP TMP.EXP 47 0.4%
THG.OBJ THG.OBJ 46 0.4%
THG.BLD THG.BLD 45 0.4%
APP.NAM APP.NAM 40 0.3%
GEO.PNT GEO.PNT 40 0.3%
TOP.NAT TOP.NAT 37 0.3%
ROL.OCC ROL.OCC 33 0.3%
WRK.EXH WRK.EXH 30 0.3%
THG.AFT THG.AFT 28 0.2%
TMP.CEN TMP.CEN 28 0.2%
GRP.INF GRP.INF 27 0.2%
unknown unknown 27 0.2%
GRP.HIS GRP.HIS 24 0.2%
APP.WKD APP.WKD 18 0.2%
GRP.REL GRP.REL 18 0.2%
TOP.HIS TOP.HIS 18 0.2%
GRP.PAR GRP.PAR 18 0.2%
TOP.LEG TOP.LEG 17 0.1%
APP.PNM APP.PNM 14 0.1%
APP.WEB APP.WEB 14 0.1%
WRK.SER WRK.SER 14 0.1%
TMP.ERA TMP.ERA 13 0.1%
WRK.DOC WRK.DOC 13 0.1%
TMP.DUR TMP.DUR 12 0.1%
APP.SOC APP.SOC 11 0.1%
QTY.MSR Measurement 11 0.1%
APP.EMAIL APP.EMAIL 11 0.1%
WRK.TIT WRK.TIT 10 0.1%
WRK.CIT WRK.CIT 9 0.1%
TMP.SET TMP.SET 9 0.1%
THG.TAX THG.TAX 9 0.1%
GRP.COL GRP.COL 8 0.1%
WRK.ARC WRK.ARC 8 0.1%
APP.PHO APP.PHO 7 0.1%
APP.TEL APP.TEL 7 0.1%
AGT.FIC AGT.FIC 7 0.1%
APP.AWD APP.AWD 7 0.1%
WRK.MUS WRK.MUS 6 0.1%
WRK.PHO WRK.PHO 6 0.1%
AGT.COL AGT.COL 6 0.1%
WRK.CIN WRK.CIN 6 0.1%
QTY.DUR QTY.DUR 5 0.0%
TMP.DAT TMP.DAT 5 0.0%
QTY.ORD QTY.ORD 4 0.0%
WRK.SOC WRK.SOC 4 0.0%
TOP.IAD TOP.IAD 4 0.0%
THG.COL THG.COL 4 0.0%
APP.KVK APP.KVK 4 0.0%
AGT.STF AGT.STF 4 0.0%
ROL.NOB ROL.NOB 4 0.0%
WRK.OBJ WRK.OBJ 4 0.0%
ROL.TTL ROL.TTL 3 0.0%
PAR PAR 3 0.0%
NAV NAV 3 0.0%
THG.MAT THG.MAT 3 0.0%
WRK.MAN WRK.MAN 3 0.0%
WRK.EML WRK.EML 2 0.0%
APP.ISBN APP.ISBN 2 0.0%
WRK.WRK WRK.WRK 2 0.0%
THG.ARC THG.ARC 2 0.0%
APP.EML APP.EML 2 0.0%
HDR HDR 2 0.0%
APP.ISL APP.ISL 2 0.0%
WRK.EVT WRK.EVT 2 0.0%
DOC.EVT DOC.EVT 2 0.0%
WRK.PER WRK.PER 2 0.0%
AGT.ART AGT.ART 2 0.0%
WRK.PUB WRK.PUB 2 0.0%
TMP.TIM TMP.TIM 2 0.0%
AGT.MYT AGT.MYT 2 0.0%
WRK.MSS WRK.MSS 2 0.0%
WRK.ORG WRK.ORG 2 0.0%
THG.FIC THG.FIC 2 0.0%
APP.WRK APP.WRK 2 0.0%
WRK.ART WRK.ART 2 0.0%
QTY.PCT QTY.PCT 1 0.0%
GRP.MIL GRP.MIL 1 0.0%
TOP.OPH TOP.OPH 1 0.0%
TMP.TRL TMP.TRL 1 0.0%
WRK.TTL WRK.TTL 1 0.0%
APP.DOI APP.DOI 1 0.0%
APP.ADR APP.ADR 1 0.0%
THG.SPC THG.SPC 1 0.0%
QTY.TRL QTY.TRL 1 0.0%
THG.NAT THG.NAT 1 0.0%
QTY.RNG QTY.RNG 1 0.0%
THG.WEB THG.WEB 1 0.0%
APP.ACR APP.ACR 1 0.0%
THG.TXT THG.TXT 1 0.0%
APP.ARC APP.ARC 1 0.0%
WRK.PRO WRK.PRO 1 0.0%
AGT.GRP AGT.GRP 1 0.0%
EVT.EVT EVT.EVT 1 0.0%
APP.PHONE APP.PHONE 1 0.0%
WRK.BLD WRK.BLD 1 0.0%
AGT.ANI AGT.ANI 1 0.0%
APP.CUR APP.CUR 1 0.0%
THG.VIS THG.VIS 1 0.0%
ROL.HON ROL.HON 1 0.0%

Entity Type Categories

Category Label Count %
APP Appellations (names, titles) 3,850 32.8%
GRP Groups (organizations) 2,336 19.9%
TOP Toponyms (places) 2,152 18.4%
TMP Temporal (dates, times) 1,111 9.5%
THG Things (objects, concepts) 901 7.7%
WRK Works (documents, collections) 691 5.9%
AGT Agents (people) 347 3.0%
QTY Quantities (numbers, measurements) 160 1.4%
ROL ROL 97 0.8%
GEO GEO 40 0.3%
unknown unknown 27 0.2%
PAR PAR 3 0.0%
NAV NAV 3 0.0%
HDR HDR 2 0.0%
DOC DOC 2 0.0%
EVT EVT 1 0.0%

Top 50 Most Common Entities

Entities appearing across multiple custodian files:

Entity Type Occurrences
Nederland THG.LNG, TOP.CTY, TOP.NAT, TOP.REG, TOP.SET 86
Nederlands THG.LNG 43
Amsterdam TOP.SET 42
Dutch THG.LNG 36
Netherlands TOP.CTY, TOP.REG, TOP.SET 24
Groningen TOP.CTY, TOP.REG, TOP.SET 21
English THG.LNG 20
Den Haag TOP.SET 17
Heel Nederland Leest APP.EXH, APP.TTL, GRP.HIS, THG.CON, THG.EVT, WRK.EXH, WRK.SER 15
Zwolle TOP.ADR, TOP.SET 15
collectie APP.COL, THG.COL, THG.CON, WRK.COL 13
Rotterdam TOP.CTY, TOP.REG, TOP.SET 13
Johan Fretz AGT.PER 13
Nederlandse THG.LNG, TOP.CTY 12
Bibliotheek APP.COL, GRP.EDU, GRP.HER, THG.CON, TOP.BLD, WRK.COL, WRK.WEB 12
Utrecht TOP.CTY, TOP.REG, TOP.SET 12
Roermond TOP.SET 11
Overijssel GRP.GOV, TOP.REG 11
Deventer TOP.SET 11
Onder de paramariboom APP.TIT, WRK.TTL, WRK.TXT 11
Beeldbank APP.COL, WRK.COL, WRK.WEB 10
Friesland TOP.CTY, TOP.REG 10
Gemeentearchief APP.TIT, APP.TTL, GRP.HER, WRK.WEB 10
Twente TOP.REG, TOP.SET 10
Leiden TOP.REG, TOP.SET 10
Noord-Holland TOP.CTY, TOP.REG 9
Tweede Wereldoorlog THG.CON, THG.EVT, TMP.ERA 9
Geldersch Landschap en Kasteelen GRP.HER 9
Collectie APP.COL, APP.EXH, WRK.COL, WRK.SER 9
Nijmegen TOP.SET 8
Limburg TOP.CTY, TOP.REG, TOP.SET 8
Enschede TOP.SET 8
Zuid-Holland GRP.GOV, TOP.REG 8
Brabant TOP.CTY, TOP.REG 8
Google GRP.COR, GRP.GOV 7
Heerlen TOP.SET 7
Maastricht TOP.SET 7
Ministerie van Algemene Zaken GRP.GOV, GRP.PAR 7
Kasteel Doorwerth APP.TTL, GRP.HER, THG.AFT, TOP.BLD 7
Delft TOP.REG, TOP.SET 7
Gelderland GRP.GOV, TOP.REG, TOP.SET 7
Schiedam TOP.SET 6
Tilburg TOP.SET 6
Amelander Musea GRP.HER 6
Alkmaar TOP.SET 6
Franeker TOP.SET 6
Ommen TOP.SET 6
Zutphen TOP.SET 6
Haarlem TOP.REG, TOP.SET 6
https://api.w.org/ APP.URL 6

Duplicate Entity Analysis

Entities that appear in 5+ different custodian files (candidates for entity linking):

Entity Files Primary Type
Nederland 86 TOP.CTY
Nederlands 43 THG.LNG
Amsterdam 42 TOP.SET
Dutch 36 THG.LNG
Netherlands 24 TOP.CTY
Groningen 21 TOP.SET
English 20 THG.LNG
Den Haag 17 TOP.SET
Heel Nederland Leest 15 APP.EXH
Zwolle 15 TOP.SET
collectie 13 WRK.COL
Rotterdam 13 TOP.SET
Johan Fretz 13 AGT.PER
Nederlandse 12 TOP.CTY
Bibliotheek 12 GRP.HER
Utrecht 12 TOP.SET
Roermond 11 TOP.SET
Overijssel 11 TOP.REG
Deventer 11 TOP.SET
Onder de paramariboom 11 WRK.TXT
Beeldbank 10 WRK.COL
Friesland 10 TOP.REG
Gemeentearchief 10 GRP.HER
Twente 10 TOP.REG
Leiden 10 TOP.SET
Noord-Holland 9 TOP.REG
Tweede Wereldoorlog 9 TMP.ERA
Geldersch Landschap en Kasteelen 9 GRP.HER
Collectie 9 WRK.COL
Nijmegen 8 TOP.SET
Limburg 8 TOP.REG
Enschede 8 TOP.SET
Zuid-Holland 8 TOP.REG
Brabant 8 TOP.REG
Google 7 GRP.COR
Heerlen 7 TOP.SET
Maastricht 7 TOP.SET
Ministerie van Algemene Zaken 7 GRP.GOV
Kasteel Doorwerth 7 GRP.HER
Delft 7 TOP.SET
Gelderland 7 TOP.REG
Schiedam 6 TOP.SET
Tilburg 6 TOP.SET
Amelander Musea 6 GRP.HER
Alkmaar 6 TOP.SET
Franeker 6 TOP.SET
Ommen 6 TOP.SET
Zutphen 6 TOP.SET
Haarlem 6 TOP.SET
https://api.w.org/ 6 APP.URL
Archieven 6 WRK.COL
Maassluis 6 TOP.SET
Dordrecht 6 TOP.SET
Arnhem 6 TOP.SET
Government of the Netherlands 6 GRP.GOV
Leeuwarden 6 TOP.SET
foto's 6 THG.PHO
Apeldoorn 6 TOP.SET
Onder de Paramariboom 6 WRK.TXT
1 november 6 TMP.DAB
november 2025 6 TMP.DRL
Zeeland 6 TOP.SET
Sinterklaas 5 APP.EXH
https://amelandermusea.nl/ 5 APP.URL
Kampen 5 TOP.SET
Breda 5 TOP.SET
archieven 5 WRK.COL
Hengelo 5 TOP.SET
Midden-Groningen 5 TOP.REG
Erfgoed 's-Hertogenbosch 5 GRP.HER
Amersfoort 5 TOP.SET
Eindhoven 5 TOP.SET
Hoorn 5 TOP.SET
Dalfsen 5 TOP.SET
Drenthe 5 TOP.REG
Oirschot 5 TOP.SET
https://www.facebook.com/GelderschLandschapKasteelen 5 APP.URL
beeldbank 5 WRK.VIS
Bollenstreek 5 TOP.REG
Medemblik 5 TOP.SET
Wageningen 5 TOP.SET
Rijksuniversiteit Groningen 5 GRP.EDU
Texel 5 TOP.SET
Provincie Overijssel 5 GRP.GOV
Collectie Overijssel 5 GRP.HER
boeken 5 THG.DOC
Flevoland 5 TOP.REG
Afspraak maken 5 APP.TIT
Papiamento 5 THG.LNG
Archief 5 APP.TIT
Venlo 5 TOP.SET

Heritage Institution Entities (GRP.HER)

These are extracted mentions of heritage institutions:

Institution Name Mentions Files
Bibliotheek 5 NL-NH-AMS-S-BNW, NL-GR-GRO-L-GFB, NL-UT-VEE-L-BVC (+2 more)
Gemeentearchief 5 NL-UT-ZEI-A-GAZ, NL-OV-STE-A-GAS-, NL-GE-TWE-A-GAV (+2 more)
Geldersch Landschap en Kasteelen 9 NL-GE-VAA-M-KC, NL-GE-ROZ-M-KR, NL-GE-DOO-M-KD- (+6 more)
Kasteel Doorwerth 2 NL-GE-DOO-M-KD-kasteel_doorwerth, NL-GE-DOO-M-KD-
Amelander Musea 6 NL-FR-HOL-M-MS, NL-FR-NES-B-NCA, NL-FR-BUR-M-LJMS (+3 more)
Erfgoed 's-Hertogenbosch 3 NL-NB-XSX-A-SAH-, NL-NB-XSX-A-SAH-stadsarchief_s_hertogenbos
Collectie Overijssel 5 NL-OV-OMM-A-GAO, NL-OV-ZWO-A-CO-collectie_overijssel, NL-OV-
Landgoed Groot ter Horne 1 NL-FR-FRA-A-GF
'Musea Zutphen: Stedelijk Museum Zutphen & Museum 2 NL-GE-ZUT-M-MZ-, NL-GE-ZUT-M-MZ-musea_zutphen
bibliotheek 1 NL-GR-VEE-A-V
OudOmmen.nl 2 NL-OV-OMM-D-WASO, NL-OV-OMM-S-O
Geheugen van Zeist 1 NL-UT-ZEI-D-GAZ
museum 2 NL-ZE-TER-M-SMS, NL-GR-UIT-M-MBB
SAMH 3 NL-ZH-AAD-A-SARM, NL-ZH-GOU-D-OA, NL-ZH-GOU-A-SAMH
Limburgs Erfgoednet 3 NL-LI-GRA-S-GB, NL-LI-NIE-S-HVN, NL-LI-HOR-S-BKSL
Huis voor de Kunsten Limburg 2 NL-LI-GRA-S-GB, NL-LI-HOR-S-BKSL
Archeologie 2 NL-GE-ZUT-A-ECZ, NL-GE-ZUT-A-RAZECZ
Rijksmuseum 4 NL-ZH-DHA-N-CCF, NL-NH-AMS-S-KOG, NL-LI-ROE-M-CHRIMAC (+1 mo
Stichting Heemkunde Tubbergen 2 NL-OV-TUB-S-HT-heemkunde_tubbergen, NL-OV-TUB-S-HT-
Fries Verzetsmuseum 2 NL-FR-LEE-M-FM-fries_museum, NL-FR-LEE-M-FM-
Staphorst 1 NL-OV-STE-L-BS
Regimentsverzameling 1 NL-NB-OIR-M-MBGPI
Zijper Museum 3 NL-NH-XZX-S-HVZ, NL-NH-SCH-M-ZO-zijper_oudheidskamer, NL-NH-
Joods Cultureel Kwartier 3 NL-NH-AMS-M-JM, NL-NH-AMS-U-JM, NL-NH-AMS-M-JCK
Streekarchief Midden-Holland 3 NL-ZH-AAD-A-SARM, NL-ZH-GOU-D-OA, NL-ZH-GOU-A-SAMH
Kunstwerk! 2 NL-GE-ZEV-M-LM, NL-GE-ZEV-L-KB
Historisch Centrum Limburg 3 NL-LI-MAA-A-HCL, NL-LI-HEE-A-HCLLH, NL-LI-HEE-A-GAH
ADNG Erfgoedcentrum voor de Nederlandse Gedragswet 1 NL-GR-GRO-A-ADCNG
Centrale Bibliotheek 3 NL-ZH-ROT-L-CBR, NL-ZH-ROT-L-BR, NL-GE-EDE-L-CE
West-Brabants Archief 3 NL-NB-BOZ-R-WBA, NL-NB-BOZ-A-WBA-, NL-NB-BOZ-A-WBA-west_brab
Biblionet Groningen 2 NL-GR-GRO-L-BG-biblionet_groningen, NL-GR-GRO-L-BG-
RegioArchief Sittard-Geleen 3 NL-LI-SIT-A-RASG-, NL-GE-AAL-A-EHDC, NL-LI-SIT-A-RASG-regioa
Stadsmuseum Veenendaal 3 NL-UT-VEE-M-MV-, NL-UT-VEE-L-BVC, NL-UT-VEE-M-MV-museum_veen
Openbare Bibliotheek Amsterdam 2 NL-NH-AMS-L-OO, NL-NH-AMS-L-OBA
Zuiderwaterlinie 1 NL-NB-GRA-S-Z
Rijksdienst voor het Cultureel Erfgoed 1 NL-UT-AME-O-RDCE
Archieven.nl 3 NL-NB-BOZ-A-WBA-, NL-NB-BOZ-A-WBA-west_brabants_archief, NL-
Nationaal Militair Museum 2 NL-UT-SOE-S-NMM, NL-GE-BUR-M-MM
Zwartewaterland 1 NL-OV-STE-L-BS
Zeeuws Archief 3 NL-ZE-VLI-A-GAV, NL-ZE-ZIE-A-GASD, NL-ZE-MID-A-ZA
Cubiss 1 NL-NB-TIL-L-C
Stichting v/h Rotterdamsche Tramweg Maatschappij R 1 NL-ZH-ROT-M-VR
Belmonte Arboretum 1 NL-GE-WAG-M-BA
Cruquius Museum 2 NL-NH-CRU-M-CM, NL-NH-CRU-M-C
Forum 1 NL-GR-GRO-L-GFB
Bibliotheek Heiloo 1 NL-NH-HEI-L-BHBH
Het Indisch Herinneringscentrum 1 NL-ZH-DHA-M-IHC
Historisch Archief Midden-Groningen 2 NL-GR-HOO-A-HAMG, NL-GR-HOO-O-MG
de Zoomerij Rheden 1 NL-GE-DIE-L-ZDBC
Stichting Brigade en Garde Prinses Irene 1 NL-NB-OIR-M-MBGPI