From 4cf3fe8a075a7ea3874d5194e7ed36a839866cf6 Mon Sep 17 00:00:00 2001 From: kempersc Date: Sat, 27 Dec 2025 13:17:40 +0100 Subject: [PATCH] Logo enrichment batch: JP+170 (5,166/12,096 = 42.7%) - 14,503 total (45.6%) --- .../.logo_enrichment_crawl4ai_checkpoint.json | 174 +++++++++++++++++- data/custodian/JP-14-OZO-M-SMMS.yaml | 19 ++ data/custodian/JP-14-RYU-L-RPL.yaml | 19 ++ ...G-A-SMA-sagamihara_municipal_archives.yaml | 32 +++- data/custodian/JP-14-SAG-A-SMA.yaml | 32 +++- data/custodian/JP-14-SAG-L-AGUMML.yaml | 32 +++- data/custodian/JP-14-SAG-L-AUCSIS.yaml | 43 ++++- data/custodian/JP-14-SAG-L-GEPC.yaml | 32 +++- data/custodian/JP-14-SAG-L-IJCL.yaml | 38 +++- data/custodian/JP-14-SAG-L-KUSNL.yaml | 32 +++- ...ritsukushikawahigashichiikisentatosho.yaml | 19 ++ ...L-sagamiharashiritsuhashimoto_library.yaml | 32 +++- ...L-sagamiharashiritsusagamiono_library.yaml | 32 +++- data/custodian/JP-14-SAG-L-SLS.yaml | 32 +++- data/custodian/JP-14-SAG-L-SWSUL.yaml | 38 +++- data/custodian/JP-14-SAG-M-MPGKU.yaml | 38 +++- data/custodian/JP-14-SAG-M-SCM.yaml | 25 +++ data/custodian/JP-14-SAG-M-SFSM.yaml | 42 ++++- data/custodian/JP-14-SAK-L-SOML.yaml | 32 +++- data/custodian/JP-14-SAK-M-SK.yaml | 35 +++- data/custodian/JP-14-SAK-M-SOBCH.yaml | 28 ++- data/custodian/JP-14-SAN-L-TBUKCL.yaml | 32 +++- data/custodian/JP-14-SAN-M-HGMH.yaml | 30 ++- data/custodian/JP-14-SAN-M-TBUYFY.yaml | 40 +++- data/custodian/JP-14-SAT-M-FHMF.yaml | 38 +++- data/custodian/JP-14-SAT-M-KIHUM.yaml | 28 ++- data/custodian/JP-14-SAT-M-MFHM.yaml | 38 +++- data/custodian/JP-14-SAT-M-SCSHM.yaml | 19 ++ data/custodian/JP-14-SAT-M-SMB.yaml | 28 ++- data/custodian/JP-14-SEK-M-KSMH.yaml | 33 ++++ data/custodian/JP-14-SHI-L-SCL.yaml | 32 +++- ...shibushishiritsu_library_anrakubunkan.yaml | 32 +++- data/custodian/JP-14-SHI-L-SLA.yaml | 32 +++- data/custodian/JP-14-SHI-L-SLK.yaml | 19 ++ data/custodian/JP-14-SHI-L-SLM.yaml | 32 +++- data/custodian/JP-14-SHI-L-SLS.yaml | 19 ++ data/custodian/JP-14-SHI-M-SCAC.yaml | 28 ++- ...shochoritsukitaurakominkantoshoshitsu.yaml | 33 ++++ ...oshochoritsushikaikominkantoshoshitsu.yaml | 46 ++++- ...shochoritsuteshimakominkantoshoshitsu.yaml | 46 ++++- data/custodian/JP-14-SHO-L-T.yaml | 33 ++++ data/custodian/JP-14-SHO-M-YAM.yaml | 36 +++- data/custodian/JP-14-SOG-L-OL.yaml | 19 ++ data/custodian/JP-14-SOS-L-SCL.yaml | 32 +++- data/custodian/JP-14-SOS-L-SLO.yaml | 32 +++- data/custodian/JP-14-SOS-L-SLT.yaml | 19 ++ ...TAK-A-KPA-kagawa_prefectural_archives.yaml | 38 +++- data/custodian/JP-14-TAK-A-KPA.yaml | 38 +++- data/custodian/JP-14-TAK-L-FEDBKUL.yaml | 32 +++- data/custodian/JP-14-TAK-L-KL.yaml | 33 +++- data/custodian/JP-14-TAK-L-KPL.yaml | 29 ++- data/custodian/JP-14-TAK-L-KUML.yaml | 35 +++- data/custodian/JP-14-TAK-L-TCPL.yaml | 19 ++ ...AK-L-TL-takamatsushiyumemirai_library.yaml | 32 +++- data/custodian/JP-14-TAK-L-TLK.yaml | 32 +++- data/custodian/JP-14-TAK-L-TLKNCT.yaml | 36 +++- data/custodian/JP-14-TAK-L-TUL.yaml | 41 ++++- data/custodian/JP-14-TAK-M-KGCSNC.yaml | 25 +++ data/custodian/JP-14-TAK-M-KM.yaml | 38 +++- data/custodian/JP-14-TAK-M-KUM.yaml | 28 ++- data/custodian/JP-14-TAK-M-RRM.yaml | 46 ++++- data/custodian/JP-14-TAK-M-SFCM.yaml | 36 +++- data/custodian/JP-14-TAK-M-SISFHM.yaml | 34 +++- data/custodian/JP-14-TAK-M-SK.yaml | 42 ++++- data/custodian/JP-14-TAK-M-TK.yaml | 25 +++ data/custodian/JP-14-TAK-M-TPDH.yaml | 32 +++- data/custodian/JP-14-TAT-L-MCL.yaml | 25 +++ ...shisakuragaokagakushusentatoshoshitsu.yaml | 46 ++++- data/custodian/JP-14-YAM-L-Y.yaml | 46 ++++- data/custodian/JP-14-YAM-L-YL.yaml | 32 +++- data/custodian/JP-14-YAM-L-YSL.yaml | 32 +++- data/custodian/JP-14-YAM-M-YCHF.yaml | 46 ++++- data/custodian/JP-14-YOK-A-STMA.yaml | 26 ++- data/custodian/JP-14-YOK-L-ALYMA.yaml | 25 +++ data/custodian/JP-14-YOK-L-BL.yaml | 38 +++- data/custodian/JP-14-YOK-L-CESSAC.yaml | 38 +++- data/custodian/JP-14-YOK-L-FULRL.yaml | 32 +++- data/custodian/JP-14-YOK-L-FULYL.yaml | 32 +++- data/custodian/JP-14-YOK-L-H.yaml | 32 +++- data/custodian/JP-14-YOK-L-ISTSL.yaml | 36 +++- ...K-L-K-kabushikigaishajiebuishikenuddo.yaml | 47 ++++- data/custodian/NL-DR-ASS-L-DNK.yaml | 134 ++++++++++++++ ...01_hanneke_bruggeman_20251227T113847Z.json | 32 ++++ ...0002_titia_siertsema_20251227T113847Z.json | 32 ++++ ...0003_jouke_haringsma_20251227T113847Z.json | 32 ++++ ...L-DNK_0004_chris_bus_20251227T113847Z.json | 32 ++++ ...-DNK_0005_ron_koelma_20251227T113847Z.json | 32 ++++ ...006_d_van_der_meulen_20251227T113847Z.json | 32 ++++ ...-DNK_0007_g_klaasens_20251227T113847Z.json | 32 ++++ ...DNK_0008_erik_drenth_20251227T113847Z.json | 32 ++++ ..._0009_rob_verhofstad_20251227T113847Z.json | 32 ++++ 91 files changed, 2848 insertions(+), 360 deletions(-) create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0001_hanneke_bruggeman_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0002_titia_siertsema_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0003_jouke_haringsma_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0004_chris_bus_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0005_ron_koelma_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0006_d_van_der_meulen_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0007_g_klaasens_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0008_erik_drenth_20251227T113847Z.json create mode 100644 data/custodian/person/entity/NL-DR-ASS-L-DNK_0009_rob_verhofstad_20251227T113847Z.json diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index 8c842c446b..23db5e59a5 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -14332,7 +14332,177 @@ "JP-14-OSH-M-SCC.yaml", "JP-14-OSH-M-SCLH.yaml", "JP-14-OSH-M-TK.yaml", - "JP-14-OSH-M-WRMS.yaml" + "JP-14-OSH-M-WRMS.yaml", + "JP-14-OSH-M-YFM.yaml", + "JP-14-OZO-M-SMMS.yaml", + "JP-14-RYU-L-RPL.yaml", + "JP-14-SAG-A-SMA-sagamihara_municipal_archives.yaml", + "JP-14-SAG-A-SMA.yaml", + "JP-14-SAG-L-ACC-araiso_community_center.yaml", + "JP-14-SAG-L-ACC-asamizo_community_center.yaml", + "JP-14-SAG-L-ACC.yaml", + "JP-14-SAG-L-AGUMML.yaml", + "JP-14-SAG-L-AUCSIS.yaml", + "JP-14-SAG-L-CCC.yaml", + "JP-14-SAG-L-GEPC.yaml", + "JP-14-SAG-L-HCC-hoshigaoka_community_center.yaml", + "JP-14-SAG-L-HCC.yaml", + "JP-14-SAG-L-IJCL.yaml", + "JP-14-SAG-L-ISASLJAEAJ.yaml", + "JP-14-SAG-L-JL.yaml", + "JP-14-SAG-L-K.yaml", + "JP-14-SAG-L-KCC-kamituruma_community_center.yaml", + "JP-14-SAG-L-KCC.yaml", + "JP-14-SAG-L-KUML.yaml", + "JP-14-SAG-L-KUSL.yaml", + "JP-14-SAG-L-KUSNL.yaml", + "JP-14-SAG-L-LLASKU.yaml", + "JP-14-SAG-L-OCC-oonodai_community_center.yaml", + "JP-14-SAG-L-OCC-oononaka_community_center.yaml", + "JP-14-SAG-L-OCC-oonuma_community_center.yaml", + "JP-14-SAG-L-OCC-oyama_community_center.yaml", + "JP-14-SAG-L-OCC.yaml", + "JP-14-SAG-L-S-sagamiharashigikaitoshoshitsu.yaml", + "JP-14-SAG-L-S-sagamiharashihokentofukushinoraiburari.yaml", + "JP-14-SAG-L-S-sagamiharashiritsuaonoharatoshoshitsu.yaml", + "JP-14-SAG-L-S-sagamiharashiritsufujinochuokominkantoshoshitsu.yaml", + "JP-14-SAG-L-S-sagamiharashiritsukushikawahigashichiikisentatosho.yaml", + "JP-14-SAG-L-S-sagamiharashiritsushiroyamakominkantoshoshitsu.yaml", + "JP-14-SAG-L-S-sagamiharashiritsutsukuichuokominkantoshoshitsu.yaml", + "JP-14-SAG-L-S.yaml", + "JP-14-SAG-L-SCC-sagamidai_community_center.yaml", + "JP-14-SAG-L-SCC.yaml", + "JP-14-SAG-L-SCILC.yaml", + "JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library.yaml", + "JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library.yaml", + "JP-14-SAG-L-SLS.yaml", + "JP-14-SAG-L-SWSUL.yaml", + "JP-14-SAG-L-TCC-tourin_community_center.yaml", + "JP-14-SAG-L-TCC.yaml", + "JP-14-SAG-L-YCC-yokoyama_community_center.yaml", + "JP-14-SAG-L-YCC.yaml", + "JP-14-SAG-M-MPGKU.yaml", + "JP-14-SAG-M-MPGTU.yaml", + "JP-14-SAG-M-SCM.yaml", + "JP-14-SAG-M-SFSM.yaml", + "JP-14-SAG-M-TMH.yaml", + "JP-14-SAK-L-SOML.yaml", + "JP-14-SAK-M-SCAM.yaml", + "JP-14-SAK-M-SK.yaml", + "JP-14-SAK-M-SOBCH.yaml", + "JP-14-SAN-L-SL-sanukishishido_library.yaml", + "JP-14-SAN-L-SL.yaml", + "JP-14-SAN-L-TBUKCL.yaml", + "JP-14-SAN-M-HGMH.yaml", + "JP-14-SAN-M-TBUYFY.yaml", + "JP-14-SAT-L-KIHUL.yaml", + "JP-14-SAT-L-S-satsumachotsurudachuokominkantoshoshitsu.yaml", + "JP-14-SAT-L-S.yaml", + "JP-14-SAT-L-SL.yaml", + "JP-14-SAT-L-SLE.yaml", + "JP-14-SAT-L-SLH.yaml", + "JP-14-SAT-L-SLI.yaml", + "JP-14-SAT-L-SLK-satsumasendaishiritsu_library_kamikoshikibunkan.yaml", + "JP-14-SAT-L-SLK-satsumasendaishiritsu_library_kashimabunkan.yaml", + "JP-14-SAT-L-SLK.yaml", + "JP-14-SAT-L-SLS-satsumasendaishiritsu_library_shimokoshikibunkan.yaml", + "JP-14-SAT-L-SLS.yaml", + "JP-14-SAT-L-SLT.yaml", + "JP-14-SAT-M-FHMF.yaml", + "JP-14-SAT-M-ILM.yaml", + "JP-14-SAT-M-KIHUM.yaml", + "JP-14-SAT-M-KNCL.yaml", + "JP-14-SAT-M-MFHM.yaml", + "JP-14-SAT-M-SCSHM.yaml", + "JP-14-SAT-M-SLM.yaml", + "JP-14-SAT-M-SMB.yaml", + "JP-14-SAT-M-SSHLM.yaml", + "JP-14-SAT-M-SSM.yaml", + "JP-14-SEK-M-KSMH.yaml", + "JP-14-SHI-L-SCL.yaml", + "JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan.yaml", + "JP-14-SHI-L-SLA.yaml", + "JP-14-SHI-L-SLK.yaml", + "JP-14-SHI-L-SLM.yaml", + "JP-14-SHI-L-SLS.yaml", + "JP-14-SHI-M-SCAC.yaml", + "JP-14-SHI-M-SKM.yaml", + "JP-14-SHO-L-SL.yaml", + "JP-14-SHO-L-T-tonoshochoritsukitaurakominkantoshoshitsu.yaml", + "JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu.yaml", + "JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu.yaml", + "JP-14-SHO-L-T.yaml", + "JP-14-SHO-L-TTL.yaml", + "JP-14-SHO-M-YAM.yaml", + "JP-14-SOG-L-OL.yaml", + "JP-14-SOG-M-OCK.yaml", + "JP-14-SOS-L-SCL.yaml", + "JP-14-SOS-L-SLO.yaml", + "JP-14-SOS-L-SLT.yaml", + "JP-14-SOS-M-OCLM.yaml", + "JP-14-SOS-M-SHFM.yaml", + "JP-14-SOS-M-TLMM.yaml", + "JP-14-TAK-A-KPA-kagawa_prefectural_archives.yaml", + "JP-14-TAK-A-KPA.yaml", + "JP-14-TAK-A-TCA-takamatsu_city_archives.yaml", + "JP-14-TAK-A-TCA.yaml", + "JP-14-TAK-L-FEDBKUL.yaml", + "JP-14-TAK-L-K.yaml", + "JP-14-TAK-L-KL.yaml", + "JP-14-TAK-L-KPAL.yaml", + "JP-14-TAK-L-KPL.yaml", + "JP-14-TAK-L-KUML.yaml", + "JP-14-TAK-L-SVCTL.yaml", + "JP-14-TAK-L-TCPL.yaml", + "JP-14-TAK-L-TL-takamatsushikagawa_library.yaml", + "JP-14-TAK-L-TL-takamatsushikokubunji_library.yaml", + "JP-14-TAK-L-TL-takamatsushimure_library.yaml", + "JP-14-TAK-L-TL-takamatsushiyumemirai_library.yaml", + "JP-14-TAK-L-TL.yaml", + "JP-14-TAK-L-TLK.yaml", + "JP-14-TAK-L-TLKNCT.yaml", + "JP-14-TAK-L-TUL.yaml", + "JP-14-TAK-M-INGMJ.yaml", + "JP-14-TAK-M-KFHMT.yaml", + "JP-14-TAK-M-KGCSNC.yaml", + "JP-14-TAK-M-KM.yaml", + "JP-14-TAK-M-KUM.yaml", + "JP-14-TAK-M-NSNMM.yaml", + "JP-14-TAK-M-NYA.yaml", + "JP-14-TAK-M-RRM.yaml", + "JP-14-TAK-M-SFCM.yaml", + "JP-14-TAK-M-SISFHM.yaml", + "JP-14-TAK-M-SK.yaml", + "JP-14-TAK-M-SMA.yaml", + "JP-14-TAK-M-TAM.yaml", + "JP-14-TAK-M-TK.yaml", + "JP-14-TAK-M-TKAF.yaml", + "JP-14-TAK-M-TPDH.yaml", + "JP-14-TAK-M-TSCP.yaml", + "JP-14-TAK-M-YJT.yaml", + "JP-14-TAR-L-TCL.yaml", + "JP-14-TAT-L-MCL.yaml", + "JP-14-YAM-L-SL.yaml", + "JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu.yaml", + "JP-14-YAM-L-Y.yaml", + "JP-14-YAM-L-YL.yaml", + "JP-14-YAM-L-YSL.yaml", + "JP-14-YAM-M-YCHF.yaml", + "JP-14-YAM-M-YFWFM.yaml", + "JP-14-YOK-A-STMA.yaml", + "JP-14-YOK-L-AGCLRCRDPP.yaml", + "JP-14-YOK-L-ALYMA.yaml", + "JP-14-YOK-L-BL.yaml", + "JP-14-YOK-L-CESSAC.yaml", + "JP-14-YOK-L-EL.yaml", + "JP-14-YOK-L-FULRL.yaml", + "JP-14-YOK-L-FULYL.yaml", + "JP-14-YOK-L-H.yaml", + "JP-14-YOK-L-HRILL.yaml", + "JP-14-YOK-L-IIS.yaml", + "JP-14-YOK-L-IMCSTKUMML.yaml", + "JP-14-YOK-L-ISTSL.yaml", + "JP-14-YOK-L-J-jieiefuienjiniaringukabushikigaishajohosenta.yaml" ], - "last_index": 499 + "last_index": 169 } \ No newline at end of file diff --git a/data/custodian/JP-14-OZO-M-SMMS.yaml b/data/custodian/JP-14-OZO-M-SMMS.yaml index 7b56bd97f0..1295701599 100644 --- a/data/custodian/JP-14-OZO-M-SMMS.yaml +++ b/data/custodian/JP-14-OZO-M-SMMS.yaml @@ -270,3 +270,22 @@ location: geonames_id: 2111278 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:35.110822+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:21:30.323081+00:00' + source_url: https://www.gsi.go.jp/MUSEUM + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gsi.go.jp/common/000222433.png + source_url: https://www.gsi.go.jp/MUSEUM + css_selector: '[document] > html.js.csstransforms3d > head > link' + retrieved_on: '2025-12-27T11:21:30.323081+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-RYU-L-RPL.yaml b/data/custodian/JP-14-RYU-L-RPL.yaml index ef26b388a7..fa47651f34 100644 --- a/data/custodian/JP-14-RYU-L-RPL.yaml +++ b/data/custodian/JP-14-RYU-L-RPL.yaml @@ -242,3 +242,22 @@ location: geonames_id: 2111258 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:35.137106+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:21:37.392128+00:00' + source_url: https://tosyo.city.ryugasaki.ibaraki.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tosyo.city.ryugasaki.ibaraki.jp/favicon.ico + source_url: https://tosyo.city.ryugasaki.ibaraki.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-27T11:21:37.392128+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAG-A-SMA-sagamihara_municipal_archives.yaml b/data/custodian/JP-14-SAG-A-SMA-sagamihara_municipal_archives.yaml index c857710090..9755a9afa1 100644 --- a/data/custodian/JP-14-SAG-A-SMA-sagamihara_municipal_archives.yaml +++ b/data/custodian/JP-14-SAG-A-SMA-sagamihara_municipal_archives.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-A-SMA-sagamihara_municipal_archives - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-A-SMA-sagamihara_municipal_archives valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-A-SMA-sagamihara_municipal_archives ghcid_numeric: 16142879488994538711 valid_from: '2025-12-06T23:38:29.578956+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAGAMIHARA MUNICIPAL ARCHIVES @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:21:43.960067+00:00' + source_url: https://www.city.sagamihara.kanagawa.jp/shisetsu/shikanren/etc/1002758.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.sagamihara.kanagawa.jp/_template_/_site_/_default_/_res/design/images/header/cmntlogo.svg + source_url: https://www.city.sagamihara.kanagawa.jp/shisetsu/shikanren/etc/1002758.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-27T11:21:43.960067+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 相模原市公式ホームページトップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-SAG-A-SMA.yaml b/data/custodian/JP-14-SAG-A-SMA.yaml index 88ce7500dd..c67fdc1d70 100644 --- a/data/custodian/JP-14-SAG-A-SMA.yaml +++ b/data/custodian/JP-14-SAG-A-SMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-A-SMA - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-A-SMA valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-A-SMA ghcid_numeric: 13599499477220058103 valid_from: '2025-12-06T23:35:50.125367+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAGAMIHARA MUNICIPAL ARCHIVES @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:21:49.043834+00:00' + source_url: https://www.city.sagamihara.kanagawa.jp/shisetsu/shikanren/etc/1002758.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.sagamihara.kanagawa.jp/_template_/_site_/_default_/_res/design/images/header/cmntlogo.svg + source_url: https://www.city.sagamihara.kanagawa.jp/shisetsu/shikanren/etc/1002758.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-27T11:21:49.043834+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 相模原市公式ホームページトップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-SAG-L-AGUMML.yaml b/data/custodian/JP-14-SAG-L-AGUMML.yaml index d3e4baa242..ea450553c5 100644 --- a/data/custodian/JP-14-SAG-L-AGUMML.yaml +++ b/data/custodian/JP-14-SAG-L-AGUMML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-AGUMML - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-AGUMML valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-AGUMML ghcid_numeric: 16048331065748781475 valid_from: '2025-12-06T23:38:54.819166+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Aoyama Gakuin University Mandai Memorial Library @@ -206,3 +207,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:22:22.212361+00:00' + source_url: http://www.agulin.aoyama.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opac.agulin.aoyama.ac.jp/iwjs0011opc/image/favicon.ico + source_url: http://www.agulin.aoyama.ac.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-27T11:22:22.212361+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAG-L-AUCSIS.yaml b/data/custodian/JP-14-SAG-L-AUCSIS.yaml index 9b9a4855aa..5299f1e955 100644 --- a/data/custodian/JP-14-SAG-L-AUCSIS.yaml +++ b/data/custodian/JP-14-SAG-L-AUCSIS.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-AUCSIS - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-AUCSIS valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-AUCSIS ghcid_numeric: 17933920981007592292 valid_from: '2025-12-06T23:38:55.538812+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Azabu University Center for Science Information Services @@ -196,7 +197,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://library.azabu-u.ac.jp/azlib/ms/ wikidata_official_website: https://library.azabu-u.ac.jp/azlib/ms/ @@ -220,3 +222,30 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:22:17.127765+00:00' + source_url: https://library.azabu-u.ac.jp/azlib/ms + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.azabu-u.ac.jp/azlib/images/center_logo.png + source_url: https://library.azabu-u.ac.jp/azlib/ms + css_selector: '[document] > html > body > header > div.inner > h1 > a > img' + retrieved_on: '2025-12-27T11:22:17.127765+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: MSポータル + - claim_type: favicon_url + claim_value: https://library.azabu-u.ac.jp/azlib/images/favicon.ico + source_url: https://library.azabu-u.ac.jp/azlib/ms + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-27T11:22:17.127765+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAG-L-GEPC.yaml b/data/custodian/JP-14-SAG-L-GEPC.yaml index 0a95904874..8604656633 100644 --- a/data/custodian/JP-14-SAG-L-GEPC.yaml +++ b/data/custodian/JP-14-SAG-L-GEPC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-GEPC - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-GEPC valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-GEPC ghcid_numeric: 2102968630116597035 valid_from: '2025-12-06T23:38:59.706472+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Gender Equality Promotion Center @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:22:29.371928+00:00' + source_url: http://www.soleilsagami.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://soleilsagami.jp/wp-content/uploads/2022/12/cropped-head_himawari-180x180.jpg + source_url: http://www.soleilsagami.jp + css_selector: '[document] > html.js > head > link:nth-of-type(19)' + retrieved_on: '2025-12-27T11:22:29.371928+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SAG-L-IJCL.yaml b/data/custodian/JP-14-SAG-L-IJCL.yaml index 52075e9ada..39596cc9f2 100644 --- a/data/custodian/JP-14-SAG-L-IJCL.yaml +++ b/data/custodian/JP-14-SAG-L-IJCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-IJCL - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-IJCL valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-IJCL ghcid_numeric: 5240597434847496067 valid_from: '2025-12-06T23:38:57.062731+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Izumi Junior College Library @@ -206,3 +207,28 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:22:41.521546+00:00' + source_url: http://www.izumi-c.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.izumi-c.ac.jp/wp-content/themes/izumi/assets/images/common/apple-touch-icon.png + source_url: http://www.izumi-c.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:22:41.521546+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 144x144 + - claim_type: og_image_url + claim_value: https://www.izumi-c.ac.jp/wp-content/themes/izumi/assets/images/common/ogp.jpg + source_url: http://www.izumi-c.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-27T11:22:41.521546+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAG-L-KUSNL.yaml b/data/custodian/JP-14-SAG-L-KUSNL.yaml index 0faa714c86..4a4ea177a7 100644 --- a/data/custodian/JP-14-SAG-L-KUSNL.yaml +++ b/data/custodian/JP-14-SAG-L-KUSNL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-KUSNL - valid_from: "2025-12-10T09:43:41Z" + valid_from: '2025-12-10T09:43:41Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-KUSNL valid_from: null - valid_to: "2025-12-10T09:43:41Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:41Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-KUSNL ghcid_numeric: 3074780744713417457 valid_from: '2025-12-06T23:38:55.493365+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kitasato University School of Nursing Library @@ -206,3 +207,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:24:19.420064+00:00' + source_url: http://www.kitasato-u.ac.jp/nrs/gakubu/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.kitasato-u.ac.jp/nrs/favicon.ico + source_url: http://www.kitasato-u.ac.jp/nrs/gakubu/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-27T11:24:19.420064+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAG-L-S-sagamiharashiritsukushikawahigashichiikisentatosho.yaml b/data/custodian/JP-14-SAG-L-S-sagamiharashiritsukushikawahigashichiikisentatosho.yaml index 71819de559..a0cd1c7555 100644 --- a/data/custodian/JP-14-SAG-L-S-sagamiharashiritsukushikawahigashichiikisentatosho.yaml +++ b/data/custodian/JP-14-SAG-L-S-sagamiharashiritsukushikawahigashichiikisentatosho.yaml @@ -154,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:25:18.456037+00:00' + source_url: http://www.city.sagamihara.kanagawa.jp/shisetsu/bunka_shakai/kouminkan/1002809.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.sagamihara.kanagawa.jp/_template_/_site_/_default_/_res/design/images/header/cmntlogo.svg + source_url: http://www.city.sagamihara.kanagawa.jp/shisetsu/bunka_shakai/kouminkan/1002809.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-27T11:25:18.456037+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 相模原市公式ホームページトップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library.yaml b/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library.yaml index 44401075e8..c06936a853 100644 --- a/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library.yaml +++ b/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-SL-sagamiharashiritsuhashimoto_library - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-SL-sagamiharashiritsuhashimoto_library valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-SL-sagamiharashiritsuhashimoto_library ghcid_numeric: 6157869278002009922 valid_from: '2025-12-06T23:38:44.086209+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAGAMIHARASHIRITSUHASHIMOTO Library @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:25:41.669317+00:00' + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_03.aspx + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/images/_favicon/180x180.png + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_03.aspx + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:25:41.669317+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library.yaml b/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library.yaml index 5eb780d070..5a49dcb564 100644 --- a/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library.yaml +++ b/data/custodian/JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-SL-sagamiharashiritsusagamiono_library - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-SL-sagamiharashiritsusagamiono_library valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-SL-sagamiharashiritsusagamiono_library ghcid_numeric: 4179128882889530340 valid_from: '2025-12-06T23:38:44.083858+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAGAMIHARASHIRITSUSAGAMIONO Library @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:25:51.886508+00:00' + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_02.aspx + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/images/_favicon/180x180.png + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_02.aspx + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:25:51.886508+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-14-SAG-L-SLS.yaml b/data/custodian/JP-14-SAG-L-SLS.yaml index c09e7f9359..c1d98df704 100644 --- a/data/custodian/JP-14-SAG-L-SLS.yaml +++ b/data/custodian/JP-14-SAG-L-SLS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-SLS - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-SLS valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-SLS ghcid_numeric: 13003117858178203846 valid_from: '2025-12-06T23:38:44.081526+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAGAMIHARASHIRITSU Library SOBUDAIBUNKAN @@ -153,3 +154,22 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:26:00.776777+00:00' + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_09.aspx + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/images/_favicon/180x180.png + source_url: https://www.lib.sagamihara.kanagawa.jp/TOSHOW/asp/library_09.aspx + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:26:00.776777+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-14-SAG-L-SWSUL.yaml b/data/custodian/JP-14-SAG-L-SWSUL.yaml index 19cec329ce..64b03b59fd 100644 --- a/data/custodian/JP-14-SAG-L-SWSUL.yaml +++ b/data/custodian/JP-14-SAG-L-SWSUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-L-SWSUL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-L-SWSUL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-L-SWSUL ghcid_numeric: 17952751382051777769 valid_from: '2025-12-06T23:38:55.559588+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sagami Women's University Library @@ -211,3 +212,28 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:26:11.439822+00:00' + source_url: http://www.sagami-wu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sagami-wu.ac.jp/common/image/app-icon.png + source_url: http://www.sagami-wu.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:26:11.439822+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sagami-wu.ac.jp/common/image/sns-icon.jpg + source_url: http://www.sagami-wu.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-27T11:26:11.439822+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAG-M-MPGKU.yaml b/data/custodian/JP-14-SAG-M-MPGKU.yaml index 30308c28d9..ce5f800c24 100644 --- a/data/custodian/JP-14-SAG-M-MPGKU.yaml +++ b/data/custodian/JP-14-SAG-M-MPGKU.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-M-MPGKU - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-M-MPGKU valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-M-MPGKU ghcid_numeric: 7433260783725382708 valid_from: '2025-12-06T23:38:33.936064+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MEDICINAL PLANT GARDEN KITASATO UNIVERSITY @@ -153,3 +154,28 @@ location: geonames_id: 11611609 geonames_name: Sagamihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:26:28.366560+00:00' + source_url: https://www.pharm.kitasato-u.ac.jp/bio-garden + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pharm.kitasato-u.ac.jp/images/favicon.ico + source_url: https://www.pharm.kitasato-u.ac.jp/bio-garden + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:26:28.366560+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.pharm.kitasato-u.ac.jp/bio-garden/images/og.jpg + source_url: https://www.pharm.kitasato-u.ac.jp/bio-garden + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-27T11:26:28.366560+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-14-SAG-M-SCM.yaml b/data/custodian/JP-14-SAG-M-SCM.yaml index 567b0b27e5..b60dab337f 100644 --- a/data/custodian/JP-14-SAG-M-SCM.yaml +++ b/data/custodian/JP-14-SAG-M-SCM.yaml @@ -316,3 +316,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/Jcwpsn_0U7A/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:26:40.251062+00:00' + source_url: https://sagamiharacitymuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sagamiharacitymuseum.jp/image/favicon.png + source_url: https://sagamiharacitymuseum.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:26:40.251062+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://sagamiharacitymuseum.jp/image/ogp.jpg + source_url: https://sagamiharacitymuseum.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-27T11:26:40.251062+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAG-M-SFSM.yaml b/data/custodian/JP-14-SAG-M-SFSM.yaml index 088de5b687..44185ab9fa 100644 --- a/data/custodian/JP-14-SAG-M-SFSM.yaml +++ b/data/custodian/JP-14-SAG-M-SFSM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAG-M-SFSM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAG-M-SFSM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAG-M-SFSM ghcid_numeric: 5613801280355840118 valid_from: '2025-12-06T23:38:33.933353+00:00' @@ -253,3 +254,36 @@ location: postal_code: 252-0246 street_address: SUIGOTANA, Sagamihara Shi Chuo Ku, Kanagawa Ken, 252-0246 normalization_timestamp: '2025-12-09T10:56:59.040818+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:27:06.326403+00:00' + source_url: https://sagamigawa-fureai.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sagamigawa-fureai.com/images/logo_aquariumsagamihara.svg + source_url: https://sagamigawa-fureai.com + css_selector: '#sitelogo > a.title > img' + retrieved_on: '2025-12-27T11:27:06.326403+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 相模川ふれあい科学館 アクアリウムさがみはら + - claim_type: favicon_url + claim_value: https://sagamigawa-fureai.com/apple-touch-icon.png + source_url: https://sagamigawa-fureai.com + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:27:06.326403+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://sagamigawa-fureai.com/images/ogimage.png + source_url: https://sagamigawa-fureai.com + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-27T11:27:06.326403+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAK-L-SOML.yaml b/data/custodian/JP-14-SAK-L-SOML.yaml index ee66e5cc43..a3707e7f1d 100644 --- a/data/custodian/JP-14-SAK-L-SOML.yaml +++ b/data/custodian/JP-14-SAK-L-SOML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAK-L-SOML - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAK-L-SOML valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAK-L-SOML ghcid_numeric: 9464058475878519469 valid_from: '2025-12-06T23:38:47.431030+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sakaide Ohashi Memorial Library @@ -151,3 +152,22 @@ location: geonames_id: 1853190 geonames_name: Sakaidechō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:27:05.657296+00:00' + source_url: http://www.city.sakaide.lg.jp/site/toshokan-top + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sakaide.lg.jp/apple-touch-icon.png + source_url: http://www.city.sakaide.lg.jp/site/toshokan-top + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-27T11:27:05.657296+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-SAK-M-SK.yaml b/data/custodian/JP-14-SAK-M-SK.yaml index 062e8e82bc..7791725276 100644 --- a/data/custodian/JP-14-SAK-M-SK.yaml +++ b/data/custodian/JP-14-SAK-M-SK.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAK-M-SK - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAK-M-SK valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAK-M-SK ghcid_numeric: 6190641041814630848 valid_from: '2025-12-06T23:38:39.406957+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAKAIDESHI KYOUDOSHIRYOUKAN @@ -191,7 +192,8 @@ wikidata_enrichment: description: museum that covers local history - id: Q96086399 label: former school building - description: building or architectural structure no longer used as a school, currently existing or not + description: building or architectural structure no longer used as a school, + currently existing or not wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -236,3 +238,22 @@ location: geonames_id: 1853190 geonames_name: Sakaidechō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:27:14.747292+00:00' + source_url: https://www.city.sakaide.lg.jp/soshiki/bunkashinkou/kyoudomusium.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sakaide.lg.jp/apple-touch-icon.png + source_url: https://www.city.sakaide.lg.jp/soshiki/bunkashinkou/kyoudomusium.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-27T11:27:14.747292+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-SAK-M-SOBCH.yaml b/data/custodian/JP-14-SAK-M-SOBCH.yaml index 7a8ed8fac4..6da873ef7c 100644 --- a/data/custodian/JP-14-SAK-M-SOBCH.yaml +++ b/data/custodian/JP-14-SAK-M-SOBCH.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAK-M-SOBCH - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAK-M-SOBCH valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAK-M-SOBCH ghcid_numeric: 12691942367325809361 valid_from: '2025-12-06T23:38:39.414390+00:00' @@ -247,3 +248,22 @@ location: postal_code: 762-0065 street_address: BANNOSUMIDORICHO, Sakaide Shi, Kagawa Ken, 762-0065 normalization_timestamp: '2025-12-09T10:56:59.206811+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:27:28.198283+00:00' + source_url: http://www.setoohhashi.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.setoohhashi.com/images/favicon.ico + source_url: http://www.setoohhashi.com + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-27T11:27:28.198283+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAN-L-TBUKCL.yaml b/data/custodian/JP-14-SAN-L-TBUKCL.yaml index c4c518727a..843ac7ae5f 100644 --- a/data/custodian/JP-14-SAN-L-TBUKCL.yaml +++ b/data/custodian/JP-14-SAN-L-TBUKCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAN-L-TBUKCL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAN-L-TBUKCL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAN-L-TBUKCL ghcid_numeric: 7239111132904058454 valid_from: '2025-12-06T23:38:56.583455+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokushima Bunri University Kagawa Campus Library @@ -204,3 +205,22 @@ location: geonames_id: 1852954 geonames_name: Sanuki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:28:00.485088+00:00' + source_url: https://lib-opac.bunri-u.ac.jp/drupal + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lib-opac.bunri-u.ac.jp/opac/images/pink/favicon.ico + source_url: https://lib-opac.bunri-u.ac.jp/drupal + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:28:00.485088+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAN-M-HGMH.yaml b/data/custodian/JP-14-SAN-M-HGMH.yaml index 0f2cb5e805..7484c6f02d 100644 --- a/data/custodian/JP-14-SAN-M-HGMH.yaml +++ b/data/custodian/JP-14-SAN-M-HGMH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAN-M-HGMH - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAN-M-HGMH valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAN-M-HGMH ghcid_numeric: 8637752902963538480 valid_from: '2025-12-06T23:38:39.431419+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HIRAGA-GENNAI MEMORIAL HALL @@ -151,3 +152,20 @@ location: geonames_id: 1852954 geonames_name: Sanuki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:28:00.776286+00:00' + source_url: https://hiragagennai.com + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://hiragagennai.com/images/slide/top01.jpg + source_url: https://hiragagennai.com + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:28:00.776286+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-14-SAN-M-TBUYFY.yaml b/data/custodian/JP-14-SAN-M-TBUYFY.yaml index 9073aada40..1289146321 100644 --- a/data/custodian/JP-14-SAN-M-TBUYFY.yaml +++ b/data/custodian/JP-14-SAN-M-TBUYFY.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAN-M-TBUYFY - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAN-M-TBUYFY valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAN-M-TBUYFY ghcid_numeric: 13259895860535661126 valid_from: '2025-12-06T23:38:39.433781+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKUSHIMA BUNRI UNIVERSITY YAKUGAKUBU FUZOKU YAKUYOUSHOKUBUTSUEN @@ -151,3 +152,30 @@ location: geonames_id: 1852954 geonames_name: Sanuki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:28:12.690534+00:00' + source_url: http://kp.bunri-u.ac.jp/course/garden + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://kp.bunri-u.ac.jp/img/logo.png + source_url: http://kp.bunri-u.ac.jp/course/garden + css_selector: '#masthead > div.header-inner > h1.site-title > a > img' + retrieved_on: '2025-12-27T11:28:12.690534+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 徳島文理大学香川薬学部 + - claim_type: favicon_url + claim_value: http://kp.bunri-u.ac.jp/wp/wp-content/uploads/2018/05/cropped-kph_logo3-180x180.jpg + source_url: http://kp.bunri-u.ac.jp/course/garden + css_selector: '[document] > html.js.svg > head > link:nth-of-type(15)' + retrieved_on: '2025-12-27T11:28:12.690534+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SAT-M-FHMF.yaml b/data/custodian/JP-14-SAT-M-FHMF.yaml index 671f85e11c..d4ee810d5f 100644 --- a/data/custodian/JP-14-SAT-M-FHMF.yaml +++ b/data/custodian/JP-14-SAT-M-FHMF.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAT-M-FHMF - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAT-M-FHMF valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAT-M-FHMF ghcid_numeric: 5111749962772057332 valid_from: '2025-12-06T23:38:40.833397+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: FOLK HERITAGE MUSEUM FURUSATOSATSUMANOYAKATA @@ -153,3 +154,28 @@ location: geonames_id: 2131582 geonames_name: Satsumae feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:34:06.398198+00:00' + source_url: https://www.satsuma-net.jp/bunka/satumanoyakata.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.satsuma-net.jp/theme/base/img_common/smartphone.png + source_url: https://www.satsuma-net.jp/bunka/satumanoyakata.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:34:06.398198+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.satsuma-net.jp/material/images/group/1/welcomepeopleMV.png + source_url: https://www.satsuma-net.jp/bunka/satumanoyakata.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:34:06.398198+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAT-M-KIHUM.yaml b/data/custodian/JP-14-SAT-M-KIHUM.yaml index 0f4f93a2d0..a6c6133b70 100644 --- a/data/custodian/JP-14-SAT-M-KIHUM.yaml +++ b/data/custodian/JP-14-SAT-M-KIHUM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAT-M-KIHUM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAT-M-KIHUM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAT-M-KIHUM ghcid_numeric: 11574746508049324605 valid_from: '2025-12-06T23:38:40.723108+00:00' @@ -223,3 +224,22 @@ geocoding: resolved_place: Amatatsucho resolved_city: Satsumasendai Shi timestamp: '2025-12-09T23:13:27.487911+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:34:15.028546+00:00' + source_url: https://www.k-junshin.ac.jp/jundai/gangu-kan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.k-junshin.ac.jp/favicon.ico + source_url: https://www.k-junshin.ac.jp/jundai/gangu-kan + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:34:15.028546+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAT-M-MFHM.yaml b/data/custodian/JP-14-SAT-M-MFHM.yaml index 6cebc2f60c..7441411891 100644 --- a/data/custodian/JP-14-SAT-M-MFHM.yaml +++ b/data/custodian/JP-14-SAT-M-MFHM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAT-M-MFHM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAT-M-MFHM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAT-M-MFHM ghcid_numeric: 11151898596933027508 valid_from: '2025-12-06T23:38:40.830138+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MIYANOJO FOLK HERITAGE MUSEUM @@ -153,3 +154,28 @@ location: geonames_id: 2131582 geonames_name: Satsumae feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:34:25.404778+00:00' + source_url: https://www.satsuma-net.jp/bunka/rekisisiryou.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.satsuma-net.jp/theme/base/img_common/smartphone.png + source_url: https://www.satsuma-net.jp/bunka/rekisisiryou.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:34:25.404778+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.satsuma-net.jp/material/images/group/1/welcomepeopleMV.png + source_url: https://www.satsuma-net.jp/bunka/rekisisiryou.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:34:25.404778+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SAT-M-SCSHM.yaml b/data/custodian/JP-14-SAT-M-SCSHM.yaml index 9af540bad0..e6bed1be26 100644 --- a/data/custodian/JP-14-SAT-M-SCSHM.yaml +++ b/data/custodian/JP-14-SAT-M-SCSHM.yaml @@ -228,3 +228,22 @@ geocoding: resolved_place: Chugo resolved_city: Satsumasendai Shi timestamp: '2025-12-09T23:13:27.542799+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:34:52.806963+00:00' + source_url: http://rekishi.satsumasendai.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://rekishi.satsumasendai.jp/sendai/wp-content/themes/sendai/images/favicon.ico + source_url: http://rekishi.satsumasendai.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-27T11:34:52.806963+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SAT-M-SMB.yaml b/data/custodian/JP-14-SAT-M-SMB.yaml index 5f72fe11a4..a14a2c1c9b 100644 --- a/data/custodian/JP-14-SAT-M-SMB.yaml +++ b/data/custodian/JP-14-SAT-M-SMB.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SAT-M-SMB - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SAT-M-SMB valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SAT-M-SMB ghcid_numeric: 7427408466898852197 valid_from: '2025-12-06T23:38:40.728578+00:00' @@ -152,3 +153,22 @@ geocoding: resolved_place: Chugo resolved_city: Satsumasendai Shi timestamp: '2025-12-09T23:13:27.615639+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:34:52.352931+00:00' + source_url: https://magokoro-bungaku.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://magokoro-bungaku.jp/application/files/9116/9570/6941/favicon.ico + source_url: https://magokoro-bungaku.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:34:52.352931+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-SEK-M-KSMH.yaml b/data/custodian/JP-14-SEK-M-KSMH.yaml index 84a25d0982..636e04db21 100644 --- a/data/custodian/JP-14-SEK-M-KSMH.yaml +++ b/data/custodian/JP-14-SEK-M-KSMH.yaml @@ -247,3 +247,36 @@ location: geonames_id: 1852760 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:35.162999+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:01.915572+00:00' + source_url: https://www.city.noda.chiba.jp/kantaro_museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.noda.chiba.jp/_template_/_site_/_default_/_res/images/header/tlogo.svg + source_url: https://www.city.noda.chiba.jp/kantaro_museum + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-27T11:35:01.915572+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 野田市 + - claim_type: favicon_url + claim_value: https://www.city.noda.chiba.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.noda.chiba.jp/kantaro_museum + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:35:01.915572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.noda.chiba.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.noda.chiba.jp/kantaro_museum + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-27T11:35:01.915572+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SHI-L-SCL.yaml b/data/custodian/JP-14-SHI-L-SCL.yaml index 0813229f2b..434458498a 100644 --- a/data/custodian/JP-14-SHI-L-SCL.yaml +++ b/data/custodian/JP-14-SHI-L-SCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHI-L-SCL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHI-L-SCL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHI-L-SCL ghcid_numeric: 14656638075417114506 valid_from: '2025-12-06T23:38:48.380407+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Shibushi City Library @@ -151,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:15.813886+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:35:15.813886+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan.yaml b/data/custodian/JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan.yaml index 0e8585b00d..340833152d 100644 --- a/data/custodian/JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan.yaml +++ b/data/custodian/JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHI-L-SLA-shibushishiritsu_library_anrakubunkan - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHI-L-SLA-shibushishiritsu_library_anrakubunkan valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHI-L-SLA-shibushishiritsu_library_anrakubunkan ghcid_numeric: 18136395368737778409 valid_from: '2025-12-06T23:38:48.391886+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUSHISHIRITSU Library ANRAKUBUNKAN @@ -151,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:25.186501+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:35:25.186501+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-L-SLA.yaml b/data/custodian/JP-14-SHI-L-SLA.yaml index fa909d2792..049c85e479 100644 --- a/data/custodian/JP-14-SHI-L-SLA.yaml +++ b/data/custodian/JP-14-SHI-L-SLA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHI-L-SLA - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHI-L-SLA valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHI-L-SLA ghcid_numeric: 9478209240003100995 valid_from: '2025-12-06T23:38:48.382645+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUSHISHIRITSU Library ARIAKEBUNKAN @@ -151,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:34.506136+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:35:34.506136+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-L-SLK.yaml b/data/custodian/JP-14-SHI-L-SLK.yaml index 9096725909..29c97bce0f 100644 --- a/data/custodian/JP-14-SHI-L-SLK.yaml +++ b/data/custodian/JP-14-SHI-L-SLK.yaml @@ -152,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:43.355745+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:35:43.355745+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-L-SLM.yaml b/data/custodian/JP-14-SHI-L-SLM.yaml index eb66781c8f..92c2794cfb 100644 --- a/data/custodian/JP-14-SHI-L-SLM.yaml +++ b/data/custodian/JP-14-SHI-L-SLM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHI-L-SLM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHI-L-SLM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHI-L-SLM ghcid_numeric: 5647870029151002597 valid_from: '2025-12-06T23:38:48.384879+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUSHISHIRITSU Library MATSUYAMABUNKAN @@ -151,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:35:51.859101+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:35:51.859101+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-L-SLS.yaml b/data/custodian/JP-14-SHI-L-SLS.yaml index 1fbde0e84c..0e5c881830 100644 --- a/data/custodian/JP-14-SHI-L-SLS.yaml +++ b/data/custodian/JP-14-SHI-L-SLS.yaml @@ -152,3 +152,22 @@ location: geonames_id: 1852588 geonames_name: Shibushi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:02.859424+00:00' + source_url: http://www.shibushicity-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibushicity-lib.jp/wp/wp-content/uploads/cropped-fav-180x180.png + source_url: http://www.shibushicity-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-27T11:36:02.859424+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SHI-M-SCAC.yaml b/data/custodian/JP-14-SHI-M-SCAC.yaml index 7543c78894..406eae515a 100644 --- a/data/custodian/JP-14-SHI-M-SCAC.yaml +++ b/data/custodian/JP-14-SHI-M-SCAC.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHI-M-SCAC - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHI-M-SCAC valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHI-M-SCAC ghcid_numeric: 757331694867596565 valid_from: '2025-12-06T23:38:40.788004+00:00' @@ -205,3 +206,22 @@ location: postal_code: 899-7104 street_address: SHIBUSHICHO ANRAKU, Shibushi Shi, Kagoshima Ken, 899-7104 normalization_timestamp: '2025-12-09T10:57:00.262914+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:10.302290+00:00' + source_url: https://www.city.shibushi.lg.jp/soshiki/22/1436.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.shibushi.lg.jp/apple-touch-icon.png + source_url: https://www.city.shibushi.lg.jp/soshiki/22/1436.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:36:10.302290+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-SHO-L-T-tonoshochoritsukitaurakominkantoshoshitsu.yaml b/data/custodian/JP-14-SHO-L-T-tonoshochoritsukitaurakominkantoshoshitsu.yaml index 3779885cc7..491e74bf3e 100644 --- a/data/custodian/JP-14-SHO-L-T-tonoshochoritsukitaurakominkantoshoshitsu.yaml +++ b/data/custodian/JP-14-SHO-L-T-tonoshochoritsukitaurakominkantoshoshitsu.yaml @@ -154,3 +154,36 @@ location: geonames_id: 1850004 geonames_name: Tonoshō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:25.400092+00:00' + source_url: https://www.town.tonosho.kagawa.jp/gyosei/soshiki/shogai/1_1/199.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.tonosho.kagawa.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.town.tonosho.kagawa.jp/gyosei/soshiki/shogai/1_1/199.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:36:25.400092+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とのしょうちょう 土庄町 Tonosho Town + - claim_type: favicon_url + claim_value: https://www.town.tonosho.kagawa.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.tonosho.kagawa.jp/gyosei/soshiki/shogai/1_1/199.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:36:25.400092+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.tonosho.kagawa.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.town.tonosho.kagawa.jp/gyosei/soshiki/shogai/1_1/199.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:36:25.400092+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu.yaml b/data/custodian/JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu.yaml index 2e19c1a06e..b06c024b76 100644 --- a/data/custodian/JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu.yaml +++ b/data/custodian/JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHO-L-T-tonoshochoritsushikaikominkantoshoshitsu ghcid_numeric: 4207591225379303723 valid_from: '2025-12-06T23:38:51.974079+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TONOSHOCHORITSUSHIKAIKOMINKANTOSHOSHITSU @@ -153,3 +154,36 @@ location: geonames_id: 1850004 geonames_name: Tonoshō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:31.999563+00:00' + source_url: http://www.town.tonosho.kagawa.jp/tns/info308.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info308.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:36:31.999563+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とのしょうちょう 土庄町 Tonosho Town + - claim_type: favicon_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info308.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:36:31.999563+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info308.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:36:31.999563+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu.yaml b/data/custodian/JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu.yaml index 4c212a67e8..5cf679cd69 100644 --- a/data/custodian/JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu.yaml +++ b/data/custodian/JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHO-L-T-tonoshochoritsuteshimakominkantoshoshitsu ghcid_numeric: 2663740419149650159 valid_from: '2025-12-06T23:38:51.976471+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TONOSHOCHORITSUTESHIMAKOMINKANTOSHOSHITSU @@ -153,3 +154,36 @@ location: geonames_id: 1850004 geonames_name: Tonoshō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:38.917843+00:00' + source_url: http://www.town.tonosho.kagawa.jp/tns/info309.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info309.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:36:38.917843+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とのしょうちょう 土庄町 Tonosho Town + - claim_type: favicon_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info309.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:36:38.917843+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info309.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:36:38.917843+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SHO-L-T.yaml b/data/custodian/JP-14-SHO-L-T.yaml index 2797150949..6460fbe364 100644 --- a/data/custodian/JP-14-SHO-L-T.yaml +++ b/data/custodian/JP-14-SHO-L-T.yaml @@ -154,3 +154,36 @@ location: geonames_id: 1850004 geonames_name: Tonoshō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:52.377352+00:00' + source_url: http://www.town.tonosho.kagawa.jp/tns/info306.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info306.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:36:52.377352+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とのしょうちょう 土庄町 Tonosho Town + - claim_type: favicon_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info306.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:36:52.377352+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tonosho.kagawa.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.tonosho.kagawa.jp/tns/info306.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:36:52.377352+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-SHO-M-YAM.yaml b/data/custodian/JP-14-SHO-M-YAM.yaml index 817cbcef12..bcc6fcef4e 100644 --- a/data/custodian/JP-14-SHO-M-YAM.yaml +++ b/data/custodian/JP-14-SHO-M-YAM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SHO-M-YAM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SHO-M-YAM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SHO-M-YAM ghcid_numeric: 12649171741206469457 valid_from: '2025-12-06T23:38:39.448258+00:00' @@ -224,3 +225,30 @@ location: postal_code: 761-4106 street_address: Shozu Gun Tonosho Cho, Kagawa Ken, 761-4106 normalization_timestamp: '2025-12-09T10:57:00.623576+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:36:59.487519+00:00' + source_url: http://meipam.net + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://meipam.net/apple-touch-icon.png + source_url: http://meipam.net + css_selector: '[document] > html.js-focus-visible.wf-barlow-n4-active > head > + link:nth-of-type(4)' + retrieved_on: '2025-12-27T11:36:59.487519+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://meipam.net/assets/images/ogp.png + source_url: http://meipam.net + css_selector: '[document] > html.js-focus-visible.wf-barlow-n4-active > head > + meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:36:59.487519+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-14-SOG-L-OL.yaml b/data/custodian/JP-14-SOG-L-OL.yaml index 3dab1f95eb..21fbba814b 100644 --- a/data/custodian/JP-14-SOG-L-OL.yaml +++ b/data/custodian/JP-14-SOG-L-OL.yaml @@ -154,3 +154,22 @@ location: geonames_id: 6822188 geonames_name: Ōsaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:37:07.478790+00:00' + source_url: http://www.town.kagoshima-osaki.lg.jp/kh-tosho/kyoiku-bunka/toshokan/goannai.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.kagoshima-osaki.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.town.kagoshima-osaki.lg.jp/kh-tosho/kyoiku-bunka/toshokan/goannai.html + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-27T11:37:07.478790+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-SOS-L-SCL.yaml b/data/custodian/JP-14-SOS-L-SCL.yaml index 601d906dd0..6c79571a4f 100644 --- a/data/custodian/JP-14-SOS-L-SCL.yaml +++ b/data/custodian/JP-14-SOS-L-SCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SOS-L-SCL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SOS-L-SCL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SOS-L-SCL ghcid_numeric: 14710958750765274861 valid_from: '2025-12-06T23:38:48.352480+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Soo City Library @@ -151,3 +152,22 @@ location: geonames_id: 1851604 geonames_name: Sōka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:37:25.627936+00:00' + source_url: http://soocity-library.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://soocity-library.jp/wordpress/wp-content/uploads/cropped-favicon-180x180.png + source_url: http://soocity-library.jp + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-27T11:37:25.627936+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SOS-L-SLO.yaml b/data/custodian/JP-14-SOS-L-SLO.yaml index b279982104..0cd01ad751 100644 --- a/data/custodian/JP-14-SOS-L-SLO.yaml +++ b/data/custodian/JP-14-SOS-L-SLO.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-SOS-L-SLO - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-SOS-L-SLO valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-SOS-L-SLO ghcid_numeric: 521008280157531922 valid_from: '2025-12-06T23:38:48.354725+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SOSHIRITSU Library OSUMIBUNKAN @@ -151,3 +152,22 @@ location: geonames_id: 1851604 geonames_name: Sōka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:37:34.949203+00:00' + source_url: http://soocity-library.jp/annex.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://soocity-library.jp/wordpress/wp-content/uploads/cropped-favicon-180x180.png + source_url: http://soocity-library.jp/annex.html + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-27T11:37:34.949203+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-SOS-L-SLT.yaml b/data/custodian/JP-14-SOS-L-SLT.yaml index 4c46b27b88..8601e8f6a1 100644 --- a/data/custodian/JP-14-SOS-L-SLT.yaml +++ b/data/custodian/JP-14-SOS-L-SLT.yaml @@ -152,3 +152,22 @@ location: geonames_id: 1851604 geonames_name: Sōka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:37:43.285700+00:00' + source_url: http://soocity-library.jp/annex.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://soocity-library.jp/wordpress/wp-content/uploads/cropped-favicon-180x180.png + source_url: http://soocity-library.jp/annex.html + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-27T11:37:43.285700+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-TAK-A-KPA-kagawa_prefectural_archives.yaml b/data/custodian/JP-14-TAK-A-KPA-kagawa_prefectural_archives.yaml index aae40a4820..faca629327 100644 --- a/data/custodian/JP-14-TAK-A-KPA-kagawa_prefectural_archives.yaml +++ b/data/custodian/JP-14-TAK-A-KPA-kagawa_prefectural_archives.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-A-KPA-kagawa_prefectural_archives - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-A-KPA-kagawa_prefectural_archives valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-A-KPA-kagawa_prefectural_archives ghcid_numeric: 6356747752400498708 valid_from: '2025-12-06T23:38:29.654668+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kagawa Prefectural Archives @@ -151,3 +152,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:37:56.734300+00:00' + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:37:56.734300+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/sns/ogp.png + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:37:56.734300+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-A-KPA.yaml b/data/custodian/JP-14-TAK-A-KPA.yaml index 5d7462ae82..b45ec90f4f 100644 --- a/data/custodian/JP-14-TAK-A-KPA.yaml +++ b/data/custodian/JP-14-TAK-A-KPA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-A-KPA - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-A-KPA valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-A-KPA ghcid_numeric: 6331211684575266027 valid_from: '2025-12-06T23:35:50.226443+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kagawa Prefectural Archives @@ -151,3 +152,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:38:04.340023+00:00' + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:38:04.340023+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/sns/ogp.png + source_url: https://www.pref.kagawa.lg.jp/bunshokan/bunshokan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:38:04.340023+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-L-FEDBKUL.yaml b/data/custodian/JP-14-TAK-L-FEDBKUL.yaml index 0b42c84d6e..5acedfc0bd 100644 --- a/data/custodian/JP-14-TAK-L-FEDBKUL.yaml +++ b/data/custodian/JP-14-TAK-L-FEDBKUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-FEDBKUL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-FEDBKUL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-FEDBKUL ghcid_numeric: 10446385615429143990 valid_from: '2025-12-06T23:38:53.777101+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Faculty of Engineering and Design Branch, Kagawa University Library @@ -206,3 +207,22 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:38:31.751761+00:00' + source_url: https://w3.lib.kagawa-u.ac.jp/?page_id=132 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://w3.lib.kagawa-u.ac.jp/opac/images/green/favicon.ico + source_url: https://w3.lib.kagawa-u.ac.jp/?page_id=132 + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:38:31.751761+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-TAK-L-KL.yaml b/data/custodian/JP-14-TAK-L-KL.yaml index fc64ee89f6..8991dab8c4 100644 --- a/data/custodian/JP-14-TAK-L-KL.yaml +++ b/data/custodian/JP-14-TAK-L-KL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-KL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-KL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-KL ghcid_numeric: 5279441677251542305 valid_from: '2025-12-06T23:38:54.233761+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KAGAWAKENRITSUHOKENIRYODAIGAKU Library @@ -187,7 +188,8 @@ wikidata_enrichment: member_of: - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://www.kagawa-puhs.ac.jp/about/facility/library.php wikidata_official_website: https://www.kagawa-puhs.ac.jp/about/facility/library.php @@ -209,3 +211,20 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:38:45.247022+00:00' + source_url: https://www.kagawa-puhs.ac.jp/about/facility/library.php + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.kagawa-puhs.ac.jp/images/common/logo.gif + source_url: https://www.kagawa-puhs.ac.jp/about/facility/library.php + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:38:45.247022+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-14-TAK-L-KPL.yaml b/data/custodian/JP-14-TAK-L-KPL.yaml index 761cfdbc34..3ea027ce65 100644 --- a/data/custodian/JP-14-TAK-L-KPL.yaml +++ b/data/custodian/JP-14-TAK-L-KPL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-KPL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-KPL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-KPL ghcid_numeric: 18426678326337843977 valid_from: '2025-12-06T23:38:47.406858+00:00' @@ -229,3 +230,23 @@ location: postal_code: 761-0393 street_address: 2217-19 HAYASHICHO, Takamatsushi, Kagawa Ken, 761-0393 normalization_timestamp: '2025-12-09T10:57:01.094190+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:38:55.521417+00:00' + source_url: http://www.library.pref.kagawa.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.library.pref.kagawa.lg.jp/kagawa_admin/wp-content/uploads/2017/10/logo.png + source_url: http://www.library.pref.kagawa.lg.jp + css_selector: '#masthead > div.inside-header.grid-container > div.site-logo:nth-of-type(3) + > a > img.header-image' + retrieved_on: '2025-12-27T11:38:55.521417+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 香川県立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-TAK-L-KUML.yaml b/data/custodian/JP-14-TAK-L-KUML.yaml index 9474122d41..cdc0d4ec35 100644 --- a/data/custodian/JP-14-TAK-L-KUML.yaml +++ b/data/custodian/JP-14-TAK-L-KUML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-KUML - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-KUML valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-KUML ghcid_numeric: 3317101940899824046 valid_from: '2025-12-06T23:38:53.771970+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kagawa University Main Library @@ -187,7 +188,8 @@ wikidata_enrichment: member_of: - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.lib.kagawa-u.ac.jp wikidata_official_website: http://www.lib.kagawa-u.ac.jp @@ -211,3 +213,22 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:39:06.026626+00:00' + source_url: https://w3.lib.kagawa-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://w3.lib.kagawa-u.ac.jp/opac/images/green/favicon.ico + source_url: https://w3.lib.kagawa-u.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:39:06.026626+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-TAK-L-TCPL.yaml b/data/custodian/JP-14-TAK-L-TCPL.yaml index 99d64d2e66..5cd38129b3 100644 --- a/data/custodian/JP-14-TAK-L-TCPL.yaml +++ b/data/custodian/JP-14-TAK-L-TCPL.yaml @@ -234,3 +234,22 @@ location: geonames_id: 2110893 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:35.190332+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:39:17.177072+00:00' + source_url: https://www.lib-takahagi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib-takahagi.jp/apple-touch-icon.png + source_url: https://www.lib-takahagi.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:39:17.177072+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-14-TAK-L-TL-takamatsushiyumemirai_library.yaml b/data/custodian/JP-14-TAK-L-TL-takamatsushiyumemirai_library.yaml index f1df0c778d..ec0bf6305e 100644 --- a/data/custodian/JP-14-TAK-L-TL-takamatsushiyumemirai_library.yaml +++ b/data/custodian/JP-14-TAK-L-TL-takamatsushiyumemirai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-TL-takamatsushiyumemirai_library - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-TL-takamatsushiyumemirai_library valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-TL-takamatsushiyumemirai_library ghcid_numeric: 7371885854351028015 valid_from: '2025-12-06T23:38:47.414049+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAMATSUSHIYUMEMIRAI Library @@ -151,3 +152,22 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:39:39.964031+00:00' + source_url: http://library.city.takamatsu.kagawa.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://library.city.takamatsu.kagawa.jp/img/logo.png + source_url: http://library.city.takamatsu.kagawa.jp + css_selector: '#TOP > header > div.wrap.header_wrap > h1.title > a > img.title_logo' + retrieved_on: '2025-12-27T11:39:39.964031+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-TAK-L-TLK.yaml b/data/custodian/JP-14-TAK-L-TLK.yaml index e692dba8db..a4ded3490a 100644 --- a/data/custodian/JP-14-TAK-L-TLK.yaml +++ b/data/custodian/JP-14-TAK-L-TLK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-TLK - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-TLK valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-TLK ghcid_numeric: 9718182640988923287 valid_from: '2025-12-06T23:38:52.788356+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAMATSUSHICHUO Library KAWARAMACHISATERAITO @@ -151,3 +152,22 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:39:53.945119+00:00' + source_url: https://library.city.takamatsu.kagawa.jp/index.asp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.takamatsu.kagawa.jp/img/logo.png + source_url: https://library.city.takamatsu.kagawa.jp/index.asp + css_selector: '#TOP > header > div.wrap.header_wrap > h1.title > a > img.title_logo' + retrieved_on: '2025-12-27T11:39:53.945119+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-TAK-L-TLKNCT.yaml b/data/custodian/JP-14-TAK-L-TLKNCT.yaml index 41eb39dd46..d5daf7b2bd 100644 --- a/data/custodian/JP-14-TAK-L-TLKNCT.yaml +++ b/data/custodian/JP-14-TAK-L-TLKNCT.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-TLKNCT - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-TLKNCT valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-TLKNCT ghcid_numeric: 9760394623103114516 valid_from: '2025-12-06T23:38:57.452589+00:00' @@ -248,3 +249,30 @@ location: postal_code: 761-8058 street_address: 355 CHOKUSHICHO, Takamatsu Shi, Kagawa Ken, 761-8058 normalization_timestamp: '2025-12-09T10:57:01.350226+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:40:01.180859+00:00' + source_url: http://www.kagawa-nct.ac.jp/libraryI + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.kagawa-nct.ac.jp/common/img/common/logo.png + source_url: http://www.kagawa-nct.ac.jp/libraryI + css_selector: '[document] > html > body > header.pc > p.logo > a > img' + retrieved_on: '2025-12-27T11:40:01.180859+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 香川高等専門学校 + - claim_type: favicon_url + claim_value: http://www.kagawa-nct.ac.jp/favicon.ico + source_url: http://www.kagawa-nct.ac.jp/libraryI + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-27T11:40:01.180859+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-TAK-L-TUL.yaml b/data/custodian/JP-14-TAK-L-TUL.yaml index fb6d7b4dac..a98a6f5f36 100644 --- a/data/custodian/JP-14-TAK-L-TUL.yaml +++ b/data/custodian/JP-14-TAK-L-TUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-L-TUL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-L-TUL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-L-TUL ghcid_numeric: 1275935692329017899 valid_from: '2025-12-06T23:38:56.589044+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Takamatsu University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.takamatsu-u.ac.jp/library/ wikidata_official_website: http://www.takamatsu-u.ac.jp/library/ @@ -214,3 +216,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:40:13.166207+00:00' + source_url: http://www.takamatsu-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.takamatsu-u.ac.jp/apple-touch-icon.png + source_url: http://www.takamatsu-u.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-27T11:40:13.166207+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: http://www.takamatsu-u.ac.jp/wp-content/themes/takamatsu-u_2024/images/banners/mainImage.png + source_url: http://www.takamatsu-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-27T11:40:13.166207+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-14-TAK-M-KGCSNC.yaml b/data/custodian/JP-14-TAK-M-KGCSNC.yaml index 2ea63733d7..8c738d2745 100644 --- a/data/custodian/JP-14-TAK-M-KGCSNC.yaml +++ b/data/custodian/JP-14-TAK-M-KGCSNC.yaml @@ -228,3 +228,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:40:34.833421+00:00' + source_url: https://www.pref.kagawa.lg.jp/goshikidaishonen/goshikidai_shonen/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.pref.kagawa.lg.jp/goshikidaishonen/goshikidai_shonen/index.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:40:34.833421+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/sns/ogp.png + source_url: https://www.pref.kagawa.lg.jp/goshikidaishonen/goshikidai_shonen/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:40:34.833421+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-M-KM.yaml b/data/custodian/JP-14-TAK-M-KM.yaml index ede01da4aa..107e8d41f6 100644 --- a/data/custodian/JP-14-TAK-M-KM.yaml +++ b/data/custodian/JP-14-TAK-M-KM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-KM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-KM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-KM ghcid_numeric: 7663051384633254633 valid_from: '2025-12-06T23:38:39.353885+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE KAGAWA MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:40:43.034801+00:00' + source_url: http://www.pref.kagawa.lg.jp/kmuseum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.kagawa.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.pref.kagawa.lg.jp/kmuseum + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:40:43.034801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/sns/ogp.png + source_url: http://www.pref.kagawa.lg.jp/kmuseum + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:40:43.034801+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-M-KUM.yaml b/data/custodian/JP-14-TAK-M-KUM.yaml index add0a74f28..7f511621a8 100644 --- a/data/custodian/JP-14-TAK-M-KUM.yaml +++ b/data/custodian/JP-14-TAK-M-KUM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-KUM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-KUM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-KUM ghcid_numeric: 6273250030571681393 valid_from: '2025-12-06T23:38:39.360875+00:00' @@ -224,3 +225,22 @@ location: postal_code: 760-8521 street_address: SAIWAICHO, Takamatsu Shi, Kagawa Ken, 760-8521 normalization_timestamp: '2025-12-09T10:57:01.573795+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:40:44.927057+00:00' + source_url: https://www.museum.kagawa-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.museum.kagawa-u.ac.jp/favicon.ico + source_url: https://www.museum.kagawa-u.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-27T11:40:44.927057+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-TAK-M-RRM.yaml b/data/custodian/JP-14-TAK-M-RRM.yaml index 998a41daa3..11d4c55792 100644 --- a/data/custodian/JP-14-TAK-M-RRM.yaml +++ b/data/custodian/JP-14-TAK-M-RRM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-RRM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-RRM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-RRM ghcid_numeric: 7182131599231625800 valid_from: '2025-12-06T23:38:39.368314+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: RURAL RESIDENCE MUSEUM @@ -151,3 +152,36 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:41:10.766445+00:00' + source_url: http://www.shikokumura.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.shikokumura.or.jp/wp-content/themes/shikokumura/assets/images/common/logo-sp.svg + source_url: http://www.shikokumura.or.jp + css_selector: '#header > div.header_inner > div.left > h1.logo > a > img.sp' + retrieved_on: '2025-12-27T11:41:10.766445+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: SHIKOKUMURA ミウゼアム + - claim_type: favicon_url + claim_value: https://www.shikokumura.or.jp/wp-content/themes/shikokumura/assets/images/common/apple-touch-icon.png + source_url: http://www.shikokumura.or.jp + css_selector: '[document] > html.no-js.ja > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:41:10.766445+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.shikokumura.or.jp/wp-content/themes/shikokumura/assets/images/common/ogimage.jpg + source_url: http://www.shikokumura.or.jp + css_selector: '[document] > html.no-js.ja > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-27T11:41:10.766445+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-14-TAK-M-SFCM.yaml b/data/custodian/JP-14-TAK-M-SFCM.yaml index 8324d5bb0c..ba2b196551 100644 --- a/data/custodian/JP-14-TAK-M-SFCM.yaml +++ b/data/custodian/JP-14-TAK-M-SFCM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-SFCM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-SFCM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-SFCM ghcid_numeric: 8209030328425704575 valid_from: '2025-12-06T23:38:39.358356+00:00' @@ -237,3 +238,30 @@ location: postal_code: 760-0073 street_address: RITSURINCHO, Takamatsu Shi, Kagawa Ken, 760-0073 normalization_timestamp: '2025-12-09T10:57:01.695212+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:41:20.162324+00:00' + source_url: https://www.my-kagawa.jp/ritsuringarden + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.my-kagawa.jp/images/icon/apple-touch-icon-180x180.png + source_url: https://www.my-kagawa.jp/ritsuringarden + css_selector: '[document] > html.wf-lato-n7-active.wf-cabin-i4-active > head > + link:nth-of-type(12)' + retrieved_on: '2025-12-27T11:41:20.162324+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: http://www.my-kagawa.jp/images/icon/ogp.png + source_url: https://www.my-kagawa.jp/ritsuringarden + css_selector: '[document] > html.wf-lato-n7-active.wf-cabin-i4-active > head > + meta:nth-of-type(16)' + retrieved_on: '2025-12-27T11:41:20.162324+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 10 diff --git a/data/custodian/JP-14-TAK-M-SISFHM.yaml b/data/custodian/JP-14-TAK-M-SISFHM.yaml index 016af52aab..fade24527a 100644 --- a/data/custodian/JP-14-TAK-M-SISFHM.yaml +++ b/data/custodian/JP-14-TAK-M-SISFHM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-SISFHM - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-SISFHM valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-SISFHM ghcid_numeric: 1336257780023150524 valid_from: '2025-12-06T23:38:39.386002+00:00' @@ -294,3 +295,28 @@ location: postal_code: 761-8001 street_address: TARUMICHO, Takamatsu Shi, Kagawa Ken, 761-8001 normalization_timestamp: '2025-12-09T10:57:01.734928+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:41:30.609978+00:00' + source_url: http://www.pref.kagawa.lg.jp/setorekishi + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.kagawa.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.pref.kagawa.lg.jp/setorekishi + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:41:30.609978+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.kagawa.lg.jp/shared/images/sns/ogp.png + source_url: http://www.pref.kagawa.lg.jp/setorekishi + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:41:30.609978+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-M-SK.yaml b/data/custodian/JP-14-TAK-M-SK.yaml index e3f54f217f..000368cdba 100644 --- a/data/custodian/JP-14-TAK-M-SK.yaml +++ b/data/custodian/JP-14-TAK-M-SK.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-SK - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-SK valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-SK ghcid_numeric: 4039380125251408348 valid_from: '2025-12-06T23:38:39.378166+00:00' @@ -234,3 +235,36 @@ location: postal_code: 761-1402 street_address: KONANCHO YUSA, Takamatsu Shi, Kagawa Ken, 761-1402 normalization_timestamp: '2025-12-09T10:57:01.769251+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:41:44.489522+00:00' + source_url: https://www.sanuki.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.sanuki.or.jp/shared/img/logo.svg + source_url: https://www.sanuki.or.jp + css_selector: '#sp-nav > div.container > div.c-spnav-bottom > p.logo > a > img' + retrieved_on: '2025-12-27T11:41:44.489522+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.sanuki.or.jp/favicon.ico + source_url: https://www.sanuki.or.jp + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(5)' + retrieved_on: '2025-12-27T11:41:44.489522+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sanuki.or.jp/images/ogimg.jpg + source_url: https://www.sanuki.or.jp + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-27T11:41:44.489522+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-14-TAK-M-TK.yaml b/data/custodian/JP-14-TAK-M-TK.yaml index aae31d1095..16e9ada9cb 100644 --- a/data/custodian/JP-14-TAK-M-TK.yaml +++ b/data/custodian/JP-14-TAK-M-TK.yaml @@ -152,3 +152,28 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:42:09.317066+00:00' + source_url: https://www.e-topia-kagawa.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.e-topia-kagawa.jp/wp/wp-content/themes/etopia_kagawa/library/images/apple-touch-icon.png + source_url: https://www.e-topia-kagawa.jp + css_selector: '[document] > html.fixedsticky-withoutfixedfixed > head > link' + retrieved_on: '2025-12-27T11:42:09.317066+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.e-topia-kagawa.jp/wp/wp-content/themes/etopia_kagawa/asset/img/ogp.png + source_url: https://www.e-topia-kagawa.jp + css_selector: '[document] > html.fixedsticky-withoutfixedfixed > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-27T11:42:09.317066+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-TAK-M-TPDH.yaml b/data/custodian/JP-14-TAK-M-TPDH.yaml index 88792beb2d..c3aa6ee683 100644 --- a/data/custodian/JP-14-TAK-M-TPDH.yaml +++ b/data/custodian/JP-14-TAK-M-TPDH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-TAK-M-TPDH - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-TAK-M-TPDH valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-TAK-M-TPDH ghcid_numeric: 16282563746976759550 valid_from: '2025-12-06T23:38:39.356101+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMAMO-PARK DISPLAY HALL @@ -151,3 +152,22 @@ location: geonames_id: 1851100 geonames_name: Takamatsu feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:42:19.109272+00:00' + source_url: http://www.takamatsujyo.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.takamatsujyo.com/takamatsujyomark.ico + source_url: http://www.takamatsujyo.com + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:42:19.109272+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-TAT-L-MCL.yaml b/data/custodian/JP-14-TAT-L-MCL.yaml index bab713ef12..376d0787dc 100644 --- a/data/custodian/JP-14-TAT-L-MCL.yaml +++ b/data/custodian/JP-14-TAT-L-MCL.yaml @@ -236,3 +236,28 @@ location: geonames_id: 10988656 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:35.218230+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:42:46.853167+00:00' + source_url: https://www.city.moriya.ibaraki.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.moriya.ibaraki.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.moriya.ibaraki.jp/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-27T11:42:46.853167+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.moriya.ibaraki.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.moriya.ibaraki.jp/library/index.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-27T11:42:46.853167+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu.yaml b/data/custodian/JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu.yaml index 48653442ea..bc127de2fb 100644 --- a/data/custodian/JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu.yaml +++ b/data/custodian/JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YAM-L-Y-yamatoshisakuragaokagakushusentatoshoshitsu ghcid_numeric: 1375715434017684495 valid_from: '2025-12-06T23:38:49.399632+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATOSHISAKURAGAOKAGAKUSHUSENTATOSHOSHITSU @@ -151,3 +152,36 @@ location: geonames_id: 11611478 geonames_name: Yamato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:42:57.048131+00:00' + source_url: http://www.city.yamato.lg.jp/web/tosho/sakura.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.yamato.lg.jp/web/tosho/sakura.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:42:57.048131+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大和市 Yamato City + - claim_type: favicon_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.yamato.lg.jp/web/tosho/sakura.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:42:57.048131+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.yamato.lg.jp/web/tosho/sakura.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:42:57.048131+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-YAM-L-Y.yaml b/data/custodian/JP-14-YAM-L-Y.yaml index 5dcd4dc1ba..42a44215c9 100644 --- a/data/custodian/JP-14-YAM-L-Y.yaml +++ b/data/custodian/JP-14-YAM-L-Y.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YAM-L-Y - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YAM-L-Y valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YAM-L-Y ghcid_numeric: 13177654905327513695 valid_from: '2025-12-06T23:38:49.397419+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATOSHITSUKIMINOGAKUSHUSENTATOSHOSHITSU @@ -151,3 +152,36 @@ location: geonames_id: 11611478 geonames_name: Yamato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:05.139436+00:00' + source_url: http://www.city.yamato.lg.jp/web/tosho/tukimino.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.yamato.lg.jp/web/tosho/tukimino.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:43:05.139436+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大和市 Yamato City + - claim_type: favicon_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.yamato.lg.jp/web/tosho/tukimino.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:43:05.139436+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.yamato.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.yamato.lg.jp/web/tosho/tukimino.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T11:43:05.139436+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-YAM-L-YL.yaml b/data/custodian/JP-14-YAM-L-YL.yaml index 08a4cfb891..c0ac85d3ed 100644 --- a/data/custodian/JP-14-YAM-L-YL.yaml +++ b/data/custodian/JP-14-YAM-L-YL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YAM-L-YL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YAM-L-YL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YAM-L-YL ghcid_numeric: 12312588356104821640 valid_from: '2025-12-06T23:38:44.149835+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATOSHIRITSU Library @@ -151,3 +152,22 @@ location: geonames_id: 11611478 geonames_name: Yamato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:16.104153+00:00' + source_url: https://yamato-bunka.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://yamato-bunka.jp/common/img/header/logo.png + source_url: https://yamato-bunka.jp/library + css_selector: '#ttlSiteLogo > a > img' + retrieved_on: '2025-12-27T11:43:16.104153+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大和市文化創造拠点 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-14-YAM-L-YSL.yaml b/data/custodian/JP-14-YAM-L-YSL.yaml index 6e2daa1c45..d8373d1b9c 100644 --- a/data/custodian/JP-14-YAM-L-YSL.yaml +++ b/data/custodian/JP-14-YAM-L-YSL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YAM-L-YSL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YAM-L-YSL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YAM-L-YSL ghcid_numeric: 15729153603995653036 valid_from: '2025-12-06T23:38:49.401901+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATOSHI SHIBUYA LIBRARY @@ -151,3 +152,22 @@ location: geonames_id: 11611478 geonames_name: Yamato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:28.244466+00:00' + source_url: https://www.yamatolib-shibuya.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.yamatolib-shibuya.jp/asset/favicon.png + source_url: https://www.yamatolib-shibuya.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:43:28.244466+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-YAM-M-YCHF.yaml b/data/custodian/JP-14-YAM-M-YCHF.yaml index 550e7ff148..1395a06cef 100644 --- a/data/custodian/JP-14-YAM-M-YCHF.yaml +++ b/data/custodian/JP-14-YAM-M-YCHF.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YAM-M-YCHF - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YAM-M-YCHF valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YAM-M-YCHF ghcid_numeric: 577515173512287869 valid_from: '2025-12-06T23:38:34.042008+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATO CITY HISTORICAL FOLKMUSEUM @@ -151,3 +152,36 @@ location: geonames_id: 11611478 geonames_name: Yamato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:35.471563+00:00' + source_url: https://www.city.yamato.lg.jp/gyosei/soshik/2017/rekishi_bunkazai/tsurumainosatorekishishiryokan/4126.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.yamato.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.yamato.lg.jp/gyosei/soshik/2017/rekishi_bunkazai/tsurumainosatorekishishiryokan/4126.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-27T11:43:35.471563+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大和市 Yamato City + - claim_type: favicon_url + claim_value: https://www.city.yamato.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.yamato.lg.jp/gyosei/soshik/2017/rekishi_bunkazai/tsurumainosatorekishishiryokan/4126.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-27T11:43:35.471563+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.yamato.lg.jp/material/images/group/46/000125409.jpg + source_url: https://www.city.yamato.lg.jp/gyosei/soshik/2017/rekishi_bunkazai/tsurumainosatorekishishiryokan/4126.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:43:35.471563+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-14-YOK-A-STMA.yaml b/data/custodian/JP-14-YOK-A-STMA.yaml index 4e2e329b0a..1ad46b6a57 100644 --- a/data/custodian/JP-14-YOK-A-STMA.yaml +++ b/data/custodian/JP-14-YOK-A-STMA.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-A-STMA - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-A-STMA valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-A-STMA ghcid_numeric: 2135422690018334906 valid_from: '2025-12-06T23:35:50.041863+00:00' @@ -270,3 +271,20 @@ location: postal_code: 226-8503 street_address: NAGATSUTACHO, Yokohama Shi Midori Ku, Kanagawa Ken, 226-8503 normalization_timestamp: '2025-12-09T10:57:02.151207+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:49.568222+00:00' + source_url: http://www.cent.titech.ac.jp/pg1166.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.cent.titech.ac.jp/_src/sc1677/83o83i815B_06.jpg + source_url: http://www.cent.titech.ac.jp/pg1166.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-27T11:43:49.568222+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-14-YOK-L-ALYMA.yaml b/data/custodian/JP-14-YOK-L-ALYMA.yaml index a460b88749..7e124eaa88 100644 --- a/data/custodian/JP-14-YOK-L-ALYMA.yaml +++ b/data/custodian/JP-14-YOK-L-ALYMA.yaml @@ -1118,3 +1118,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/pa6d5GeWuP0/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:43:59.420373+00:00' + source_url: https://yokohama.art.museum/facility/art-library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://yokohama.art.museum/wp-content/themes/yokobi/assets/images/common/favicon.ico + source_url: https://yokohama.art.museum/facility/art-library + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-27T11:43:59.420373+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://yokohama.art.museum/wp-content/uploads/2023/11/ogp.jpg + source_url: https://yokohama.art.museum/facility/art-library + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-27T11:43:59.420373+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-14-YOK-L-BL.yaml b/data/custodian/JP-14-YOK-L-BL.yaml index 5df7085a90..7133442333 100644 --- a/data/custodian/JP-14-YOK-L-BL.yaml +++ b/data/custodian/JP-14-YOK-L-BL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-BL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-BL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-BL ghcid_numeric: 11526651635345178060 valid_from: '2025-12-06T23:38:59.044132+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Broadcast Library @@ -153,3 +154,28 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:44:08.074360+00:00' + source_url: https://www.bpcj.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.bpcj.or.jp/wp-content/uploads/2024/06/logo_BL_white.png + source_url: https://www.bpcj.or.jp + css_selector: '#colophon > nav.mb-5.mb-lg-0 > a.navbar-brand.d-inline-flex > img' + retrieved_on: '2025-12-27T11:44:08.074360+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 放送ライブラリー BROADCAST LIBRARY + - claim_type: og_image_url + claim_value: https://www.bpcj.or.jp/wp-content/uploads/2024/06/logo_BL_ogp.png + source_url: https://www.bpcj.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-27T11:44:08.074360+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-14-YOK-L-CESSAC.yaml b/data/custodian/JP-14-YOK-L-CESSAC.yaml index 5d2cf98f29..e0cd0f7818 100644 --- a/data/custodian/JP-14-YOK-L-CESSAC.yaml +++ b/data/custodian/JP-14-YOK-L-CESSAC.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-CESSAC - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-CESSAC valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-CESSAC ghcid_numeric: 434756304188964788 valid_from: '2025-12-06T23:38:58.067226+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Center for Economic and Social Studies in Asia (CESSA) @@ -206,3 +207,28 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:44:17.609281+00:00' + source_url: http://www.econ.ynu.ac.jp/cessa/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.econ.ynu.ac.jp/apple-touch-icon.png + source_url: http://www.econ.ynu.ac.jp/cessa/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T11:44:17.609281+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.econ.ynu.ac.jp/cessa/assets/images/ogp_img.png + source_url: http://www.econ.ynu.ac.jp/cessa/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-27T11:44:17.609281+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-14-YOK-L-FULRL.yaml b/data/custodian/JP-14-YOK-L-FULRL.yaml index 692520db3d..03be39f7fe 100644 --- a/data/custodian/JP-14-YOK-L-FULRL.yaml +++ b/data/custodian/JP-14-YOK-L-FULRL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-FULRL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-FULRL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-FULRL ghcid_numeric: 3740781547556719564 valid_from: '2025-12-06T23:38:55.576005+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ferris University Library Ryokuen Library @@ -206,3 +207,22 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:44:46.186687+00:00' + source_url: http://www.library.ferris.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.library.ferris.ac.jp/favicon.png + source_url: http://www.library.ferris.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(79)' + retrieved_on: '2025-12-27T11:44:46.186687+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-YOK-L-FULYL.yaml b/data/custodian/JP-14-YOK-L-FULYL.yaml index b202041389..c276fbbdd6 100644 --- a/data/custodian/JP-14-YOK-L-FULYL.yaml +++ b/data/custodian/JP-14-YOK-L-FULYL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-FULYL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-FULYL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-FULYL ghcid_numeric: 2280303191329748292 valid_from: '2025-12-06T23:38:55.578639+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ferris University Library Yamate Library @@ -206,3 +207,22 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:45:06.820546+00:00' + source_url: http://www.library.ferris.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.library.ferris.ac.jp/favicon.png + source_url: http://www.library.ferris.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(79)' + retrieved_on: '2025-12-27T11:45:06.820546+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-14-YOK-L-H.yaml b/data/custodian/JP-14-YOK-L-H.yaml index 5bbfa7a2c9..971da475e9 100644 --- a/data/custodian/JP-14-YOK-L-H.yaml +++ b/data/custodian/JP-14-YOK-L-H.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-H - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-H valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-H ghcid_numeric: 10808422597801825826 valid_from: '2025-12-06T23:38:49.321072+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HEMIKOMYUNITEISENTATOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 1848313 geonames_name: Yokosuka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-27T11:45:03.714072+00:00' + source_url: https://www.city.yokosuka.kanagawa.jp/2484/sisetu/fc00000447.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.yokosuka.kanagawa.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.yokosuka.kanagawa.jp/2484/sisetu/fc00000447.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-27T11:45:03.714072+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-14-YOK-L-ISTSL.yaml b/data/custodian/JP-14-YOK-L-ISTSL.yaml index 07ff4ee08d..c571d5b6ef 100644 --- a/data/custodian/JP-14-YOK-L-ISTSL.yaml +++ b/data/custodian/JP-14-YOK-L-ISTSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-ISTSL - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-ISTSL valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-ISTSL ghcid_numeric: 13242971132174860192 valid_from: '2025-12-06T23:38:53.367821+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Institute of Science Tokyo, Suzukakedai Library @@ -182,7 +183,8 @@ wikidata_enrichment: part_of: id: Q587326 label: Tokyo Institute of Technology - description: national top-tier research university located in Greater Tokyo Area, Japan + description: national top-tier research university located in Greater Tokyo + Area, Japan wikidata_web: official_website: http://www.libra.titech.ac.jp wikidata_official_website: http://www.libra.titech.ac.jp @@ -206,3 +208,23 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T12:02:58.085123+00:00' + source_url: https://www.libra.titech.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.libra.titech.ac.jp/apple-touch-icon.png + source_url: https://www.libra.titech.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-27T12:02:58.085123+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 + 4 diff --git a/data/custodian/JP-14-YOK-L-K-kabushikigaishajiebuishikenuddo.yaml b/data/custodian/JP-14-YOK-L-K-kabushikigaishajiebuishikenuddo.yaml index b93aaec17c..25cc9f96ed 100644 --- a/data/custodian/JP-14-YOK-L-K-kabushikigaishajiebuishikenuddo.yaml +++ b/data/custodian/JP-14-YOK-L-K-kabushikigaishajiebuishikenuddo.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-14-YOK-L-K-kabushikigaishajiebuishikenuddo - valid_from: "2025-12-10T09:43:42Z" + valid_from: '2025-12-10T09:43:42Z' valid_to: null - reason: "Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per ISO 3166-2:JP" + reason: Corrected region code from JP-KA (abbreviation) to JP-14 (Kanagawa) per + ISO 3166-2:JP - ghcid: JP-KA-YOK-L-K-kabushikigaishajiebuishikenuddo valid_from: null - valid_to: "2025-12-10T09:43:42Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:42Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-KA-YOK-L-K-kabushikigaishajiebuishikenuddo ghcid_numeric: 14943308591702422415 valid_from: '2025-12-06T23:38:59.015121+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KABUSHIKIGAISHAJIEBUISHIKENUDDO @@ -153,3 +154,37 @@ location: geonames_id: 1848354 geonames_name: Yokohama feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-27T12:16:58.712290+00:00' + source_url: http://www.jvckenwood.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.jvckenwood.com/content/dam/jvckenwood/top/logo/jvckenwood_j_w.png + source_url: http://www.jvckenwood.com + css_selector: '#jkc_header > header.jvc_header > div.jkw-nav2 > div.navleft2 > + a > img' + retrieved_on: '2025-12-27T12:16:58.712290+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: JVCケンウッド + - claim_type: favicon_url + claim_value: http://www.jvckenwood.com/apple-touch-icon.png + source_url: http://www.jvckenwood.com + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-27T12:16:58.712290+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.jvckenwood.com/content/JVCKENWOOD/jp.thumb.480.300.png + source_url: http://www.jvckenwood.com + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-27T12:16:58.712290+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/NL-DR-ASS-L-DNK.yaml b/data/custodian/NL-DR-ASS-L-DNK.yaml index 80f4fae432..62c2652101 100644 --- a/data/custodian/NL-DR-ASS-L-DNK.yaml +++ b/data/custodian/NL-DR-ASS-L-DNK.yaml @@ -807,3 +807,137 @@ web_enrichment: xpath_match_score: 0.8 extraction_method: address_container html_file: web/NL/DR/ASS/L/DNK/www.dnk.nl_index.html + +person_observations: + staff: + - person_id: NL-DR-ASS-L-DNK_0001_hanneke_bruggeman + person_name: Hanneke Bruggeman + role_title: Directeur-bestuurder + role_en: Director-CEO + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/over-dnk/ + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + linkedin_profile_url: https://nl.linkedin.com/in/hanneke-bruggeman-3444907 + person_profile_path: data/custodian/person/entity/NL-DR-ASS-L-DNK_0001_hanneke_bruggeman_20251227T120000Z.json + notes: Solo directeur since Oct 2017, previously library director since 2012 + + - person_id: NL-DR-ASS-L-DNK_0002_titia_siertsema + person_name: Titia Siertsema + role_title: Voorzitter Raad van Toezicht + role_en: Chair Supervisory Board + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/raad-van-toezicht + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: RvT chair + + - person_id: NL-DR-ASS-L-DNK_0003_jouke_haringsma + person_name: Jouke Haringsma + role_title: Lid Raad van Toezicht + role_en: Member Supervisory Board - Audit Committee + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/raad-van-toezicht + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Financial background, Haringsma Financieel Management, owner of Winel Industry Group + + - person_id: NL-DR-ASS-L-DNK_0004_chris_bus + person_name: Chris Bus + role_title: Lid Raad van Toezicht + role_en: Member Supervisory Board - Remuneration Committee + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/raad-van-toezicht + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Former interim CEO Tooling Holland, former Rabobank Assen director + + - person_id: NL-DR-ASS-L-DNK_0005_ron_koelma + person_name: Ron Koelma + role_title: Duurzaamheidscoördinator + role_en: Sustainability Coordinator + heritage_relevant: true + heritage_type: D + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/over-dnk/ + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Sustainability coordinator + + - person_id: NL-DR-ASS-L-DNK_0006_d_van_der_meulen + person_name: D. van der Meulen + role_title: Lid Raad van Toezicht + role_en: Member Supervisory Board - Audit Committee + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/raad-van-toezicht + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Audit commission member + + - person_id: NL-DR-ASS-L-DNK_0007_g_klaasens + person_name: G. Klaasens + role_title: Lid Raad van Toezicht + role_en: Member Supervisory Board - Remuneration Committee + heritage_relevant: true + heritage_type: L + current: true + affiliation_provenance: + source_url: https://www.dnk.nl/info-contact/raad-van-toezicht + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Remuneration committee member + + - person_id: NL-DR-ASS-L-DNK_0008_erik_drenth + person_name: Erik Drenth + role_title: Former lid Raad van Toezicht + role_en: Former Member Supervisory Board + heritage_relevant: true + heritage_type: L + current: false + affiliation_provenance: + source_url: https://www.dnk.nl/nieuws/rvt-compleet/ + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Terms expired 2021, replaced by Haringsma + + - person_id: NL-DR-ASS-L-DNK_0009_rob_verhofstad + person_name: Rob Verhofstad + role_title: Former lid Raad van Toezicht + role_en: Former Member Supervisory Board + heritage_relevant: true + heritage_type: L + current: false + affiliation_provenance: + source_url: https://www.dnk.nl/nieuws/rob-verhofstad-treedt-toe-tot-de-raad-van-toezicht-van-dnk/ + retrieved_on: '2025-12-27T12:00:00Z' + retrieval_agent: linkup + notes: Left summer 2021 after 4 years + +# Added person_observations section based on Linkup discovery (2025-12-27) +# Personnel extracted: +# - Hanneke Bruggeman (Director-CEO) - current +# - Titia Siertsema (Chair RvT) - current +# - Jouke Haringsma (Audit Committee) - current +# - Chris Bus (Remuneration Committee) - current +# - Ron Koelma (Sustainability Coordinator) - current +# - D. van der Meulen (Audit Committee) - current +# - G. Klaasens (Remuneration Committee) - current +# - Erik Drenth (Audit Committee - former, terms expired 2021) +# - Rob Verhofstad (Audit Committee - former, left summer 2021) + diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0001_hanneke_bruggeman_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0001_hanneke_bruggeman_20251227T113847Z.json new file mode 100644 index 0000000000..b612f989fd --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0001_hanneke_bruggeman_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0001_hanneke_bruggeman", + "foaf:name": "Hanneke Bruggeman", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Directeur-bestuurder", + "schema:jobTitle": "Directeur-bestuurder", + "schema:jobTitle@en": "Director-CEO" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Hanneke Bruggeman", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.702134+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Solo directeur since Oct 2017, previously library director since 2012" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0002_titia_siertsema_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0002_titia_siertsema_20251227T113847Z.json new file mode 100644 index 0000000000..99853f54c9 --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0002_titia_siertsema_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0002_titia_siertsema", + "foaf:name": "Titia Siertsema", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Voorzitter Raad van Toezicht", + "schema:jobTitle": "Voorzitter Raad van Toezicht", + "schema:jobTitle@en": "Chair Supervisory Board" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Titia Siertsema", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.705817+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Mentioned as RvT chair" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0003_jouke_haringsma_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0003_jouke_haringsma_20251227T113847Z.json new file mode 100644 index 0000000000..2c48f65510 --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0003_jouke_haringsma_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0003_jouke_haringsma", + "foaf:name": "Jouke Haringsma", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Lid Raad van Toezicht", + "schema:jobTitle": "Lid Raad van Toezicht", + "schema:jobTitle@en": "Member Supervisory Board - Audit Committee" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Jouke Haringsma", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.705991+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Financial background, Haringsma Financieel Management, owner of Winel Industry Group" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0004_chris_bus_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0004_chris_bus_20251227T113847Z.json new file mode 100644 index 0000000000..3b6a036769 --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0004_chris_bus_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0004_chris_bus", + "foaf:name": "Chris Bus", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Lid Raad van Toezicht", + "schema:jobTitle": "Lid Raad van Toezicht", + "schema:jobTitle@en": "Member Supervisory Board - Remuneration Committee" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Chris Bus", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.706173+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Former interim CEO Tooling Holland, former Rabobank Assen director" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0005_ron_koelma_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0005_ron_koelma_20251227T113847Z.json new file mode 100644 index 0000000000..f9a8f8eadd --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0005_ron_koelma_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0005_ron_koelma", + "foaf:name": "Ron Koelma", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Duurzaamheidscoördinator", + "schema:jobTitle": "Duurzaamheidscoördinator", + "schema:jobTitle@en": "Sustainability Coordinator" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Ron Koelma", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.706330+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Sustainability coordinator" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0006_d_van_der_meulen_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0006_d_van_der_meulen_20251227T113847Z.json new file mode 100644 index 0000000000..decd9807dc --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0006_d_van_der_meulen_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0006_d_van_der_meulen", + "foaf:name": "D. van der Meulen", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Lid Raad van Toezicht", + "schema:jobTitle": "Lid Raad van Toezicht", + "schema:jobTitle@en": "Member Supervisory Board - Audit Committee" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "D. van der Meulen", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.706874+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0007_g_klaasens_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0007_g_klaasens_20251227T113847Z.json new file mode 100644 index 0000000000..a44c75e0e5 --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0007_g_klaasens_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0007_g_klaasens", + "foaf:name": "G. Klaasens", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Lid Raad van Toezicht", + "schema:jobTitle": "Lid Raad van Toezicht", + "schema:jobTitle@en": "Member Supervisory Board - Remuneration Committee" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "G. Klaasens", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.707441+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0008_erik_drenth_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0008_erik_drenth_20251227T113847Z.json new file mode 100644 index 0000000000..a6a5088e9f --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0008_erik_drenth_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0008_erik_drenth", + "foaf:name": "Erik Drenth", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Former lid Raad van Toezicht", + "schema:jobTitle": "Former lid Raad van Toezicht", + "schema:jobTitle@en": "Former Member Supervisory Board" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Erik Drenth", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.707965+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Terms expired 2021, replaced by Haringsma" +} \ No newline at end of file diff --git a/data/custodian/person/entity/NL-DR-ASS-L-DNK_0009_rob_verhofstad_20251227T113847Z.json b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0009_rob_verhofstad_20251227T113847Z.json new file mode 100644 index 0000000000..c14641daa5 --- /dev/null +++ b/data/custodian/person/entity/NL-DR-ASS-L-DNK_0009_rob_verhofstad_20251227T113847Z.json @@ -0,0 +1,32 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/" + }, + "person_id": "NL-DR-ASS-L-DNK_0009_rob_verhofstad", + "foaf:name": "Rob Verhofstad", + "affiliations": { + "org:organization": { + "id": "https://glam.example.org/custodian/NL-DR-ASS-L-DNK", + "ghcid": "NL-DR-ASS-L-DNK", + "name": "De Nieuwe Kolk" + }, + "org:role": "Former lid Raad van Toezicht", + "schema:jobTitle": "Former lid Raad van Toezicht", + "schema:jobTitle@en": "Former Member Supervisory Board" + }, + "web_claims": [ + { + "claim_type": "full_name", + "claim_value": "Rob Verhofstad", + "source_url": "https://www.dnk.nl/info-contact/over-dnk/", + "retrieved_on": "2025-12-27T11:38:47.708174+00:00", + "xpath": "/html/body", + "html_file": "web/NL-DR-ASS-L-DNK/dnk.nl/over-dnk.html", + "xpath_match_score": 1.0, + "retrieval_agent": "linkup" + } + ], + "notes": "Left summer 2021 after 4 years" +} \ No newline at end of file