diff --git a/data/extraction_checkpoint.json b/data/extraction_checkpoint.json
index b646e3397a..286bcd178a 100644
--- a/data/extraction_checkpoint.json
+++ b/data/extraction_checkpoint.json
@@ -1 +1 @@
-{"processed_ids": ["0025/dewemme.nl", "0111/vlieland.nl", "0021/historischeverenigingnijeveen.nl", "0223/stadskasteelzaltbommel.nl", "0047/hetflevolandsarchief.nl", "0030/gevangenismuseum.nl", "0102/streekargyf.nl", "0063/kazemattenmuseum.nl", "0039/oudmeppel.nl", "0133/despitkeet.nl", "0101/noardeast-fryslan.nl", "0184/gemeentearchief.ede.nl", "0162/weeshuismuseum.nl", "0232/muzieum.nl", "0012/meppel.nl", "0036/historieruinerwold.nl", "0142/regionaalarchiefnijmegen.nl", "0213/museumkinderdorpneerbosch.nl", "0068/museummoddergat.nl", "0014/gemeentenoordenveld.nl", "0050/museumschokland.nl", "0013/middendrenthe.nl", "0243/ambachtenmuseum.nl", "0147/museumoldebroek.nl", "0043/archief-optspoor.nl", "0094/defryskemarren.nl", "0156/rozet.nl", "0253/singerlaren.nl", "0122/museumbelvedere.nl", "0057/historischdronten.nl", "0196/kasteeldoornenburg.nl", "0095/noardeast-fryslan.nl", "0023/miramar-zeemuseum.nl", "0187/dewarmoes.nl", "0168/wageningen.nl", "0130/natuurmuseumfryslan.nl", "0072/museumdrachten.nl", "0079/natuurcentrumameland.nl", "0088/landbouwmuseumfriesland.nl", "0110/t-diel.nl", "0120/modelspoormuseum.nl", "0075/museumhindeloopen.nl", "0204/krollermuller.nl", "0052/nieuwland-experience.nl", "0062/hannemahuis.nl", "0085/dekruidhof.nl", "0173/heemkundekringrijnwaarden.nl", "0177/historischmuseumede.nl"], "last_updated": "2025-12-05T14:30:01.710274+00:00", "processed_count": 160, "successful_count": 160}
\ No newline at end of file
+{"processed_ids": ["0025/dewemme.nl", "0111/vlieland.nl", "0021/historischeverenigingnijeveen.nl", "0258/stadsmuseum-harderwijk.nl", "0223/stadskasteelzaltbommel.nl", "0047/hetflevolandsarchief.nl", "0030/gevangenismuseum.nl", "0102/streekargyf.nl", "0063/kazemattenmuseum.nl", "0039/oudmeppel.nl", "0133/despitkeet.nl", "0225/slotloevestein.nl", "0101/noardeast-fryslan.nl", "0184/gemeentearchief.ede.nl", "0162/weeshuismuseum.nl", "0232/muzieum.nl", "0012/meppel.nl", "0036/historieruinerwold.nl", "0142/regionaalarchiefnijmegen.nl", "0213/museumkinderdorpneerbosch.nl", "0068/museummoddergat.nl", "0014/gemeentenoordenveld.nl", "0050/museumschokland.nl", "0214/korpsrijdendeartillerie.nl", "0013/middendrenthe.nl", "0243/ambachtenmuseum.nl", "0147/museumoldebroek.nl", "0043/archief-optspoor.nl", "0094/defryskemarren.nl", "0156/rozet.nl", "0253/singerlaren.nl", "0122/museumbelvedere.nl", "0057/historischdronten.nl", "0196/kasteeldoornenburg.nl", "0095/noardeast-fryslan.nl", "0023/miramar-zeemuseum.nl", "0247/paleishetloo.nl", "0187/dewarmoes.nl", "0168/wageningen.nl", "0194/kasteel-ammersoyen.nl", "0235/nationaalorgelmuseum.nl", "0204/kmm.nl", "0130/natuurmuseumfryslan.nl", "0072/museumdrachten.nl", "0079/natuurcentrumameland.nl", "0088/landbouwmuseumfriesland.nl", "0110/t-diel.nl", "0120/modelspoormuseum.nl", "0075/museumhindeloopen.nl", "0204/krollermuller.nl", "0052/nieuwland-experience.nl", "0062/hannemahuis.nl", "0085/dekruidhof.nl", "0173/heemkundekringrijnwaarden.nl", "0267/geelvinckhinlopenhuis.nl", "0177/historischmuseumede.nl"], "last_updated": "2025-12-05T14:49:59.250604+00:00", "processed_count": 240, "successful_count": 240}
\ No newline at end of file
diff --git a/data/nde/enriched/entries/0134_Q2530771.yaml b/data/nde/enriched/entries/0134_Q2530771.yaml
index 0cf7c85bdd..8be2d02347 100644
--- a/data/nde/enriched/entries/0134_Q2530771.yaml
+++ b/data/nde/enriched/entries/0134_Q2530771.yaml
@@ -3617,3 +3617,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:16:27.726466+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.kazemattenmuseum.nl/
+ directory: web/0134/kazemattenmuseum.nl
+ archive_timestamp: '2025-12-05T14:31:53.312853+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:31:58.455377+00:00'
diff --git a/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml b/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml
index ab73199150..9cb5923162 100644
--- a/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml
+++ b/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml
@@ -1349,3 +1349,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:16:29.800864+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.kadaster.nl/
+ directory: web/0139/kadaster.nl
+ archive_timestamp: '2025-12-05T14:31:59.601815+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:02.668708+00:00'
diff --git a/data/nde/enriched/entries/0144_Q2710899.yaml b/data/nde/enriched/entries/0144_Q2710899.yaml
index 54e096adde..b75eec19c8 100644
--- a/data/nde/enriched/entries/0144_Q2710899.yaml
+++ b/data/nde/enriched/entries/0144_Q2710899.yaml
@@ -3259,3 +3259,10 @@ genealogiewerkbalk_enrichment:
provincial_archive:
name: Gelders Archief
website: https://www.geldersarchief.nl/
+web_enrichment:
+ web_archives:
+ - url: https://nationaalonderduikmuseum.nl
+ directory: web/0144/nationaalonderduikmuseum.nl
+ archive_timestamp: '2025-12-05T14:32:03.823311+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:07.301226+00:00'
diff --git a/data/nde/enriched/entries/0145_Q2654815.yaml b/data/nde/enriched/entries/0145_Q2654815.yaml
index 658f66a52f..0204e52904 100644
--- a/data/nde/enriched/entries/0145_Q2654815.yaml
+++ b/data/nde/enriched/entries/0145_Q2654815.yaml
@@ -7637,3 +7637,10 @@ genealogiewerkbalk_enrichment:
provincial_archive:
name: Gelders Archief
website: https://www.geldersarchief.nl/
+web_enrichment:
+ web_archives:
+ - url: http://www.antonpieckmuseum.nl
+ directory: web/0145/antonpieckmuseum.nl
+ archive_timestamp: '2025-12-05T14:32:08.642519+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:11.173228+00:00'
diff --git a/data/nde/enriched/entries/0148_Q69725772.yaml b/data/nde/enriched/entries/0148_Q69725772.yaml
index 2fbb0308d2..3a6327860c 100644
--- a/data/nde/enriched/entries/0148_Q69725772.yaml
+++ b/data/nde/enriched/entries/0148_Q69725772.yaml
@@ -13289,3 +13289,10 @@ genealogiewerkbalk_enrichment:
provincial_archive:
name: Gelders Archief
website: https://www.geldersarchief.nl/
+web_enrichment:
+ web_archives:
+ - url: https://erfgoedgelderland.nl/
+ directory: web/0148/erfgoedgelderland.nl
+ archive_timestamp: '2025-12-05T14:32:12.743480+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:17.430889+00:00'
diff --git a/data/nde/enriched/entries/0152_Q69725772.yaml b/data/nde/enriched/entries/0152_Q69725772.yaml
index fa82055b9f..556ed96066 100644
--- a/data/nde/enriched/entries/0152_Q69725772.yaml
+++ b/data/nde/enriched/entries/0152_Q69725772.yaml
@@ -13261,3 +13261,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:16:35.572218+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://erfgoedgelderland.nl/
+ directory: web/0152/erfgoedgelderland.nl
+ archive_timestamp: '2025-12-05T14:32:19.067354+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:23.449204+00:00'
diff --git a/data/nde/enriched/entries/0153_Q3448774.yaml b/data/nde/enriched/entries/0153_Q3448774.yaml
index 600845f2ef..4de404cc24 100644
--- a/data/nde/enriched/entries/0153_Q3448774.yaml
+++ b/data/nde/enriched/entries/0153_Q3448774.yaml
@@ -7465,3 +7465,10 @@ genealogiewerkbalk_enrichment:
provincial_archive:
name: Gelders Archief
website: https://www.geldersarchief.nl/
+web_enrichment:
+ web_archives:
+ - url: https://www.ecal.nu
+ directory: web/0153/ecal.nu
+ archive_timestamp: '2025-12-05T14:32:24.933150+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:32:28.138552+00:00'
diff --git a/data/nde/enriched/entries/0155_Q13636575.yaml b/data/nde/enriched/entries/0155_Q13636575.yaml
index 150f05a0c5..a292d27549 100644
--- a/data/nde/enriched/entries/0155_Q13636575.yaml
+++ b/data/nde/enriched/entries/0155_Q13636575.yaml
@@ -6428,3 +6428,10 @@ genealogiewerkbalk_enrichment:
provincial_archive:
name: Gelders Archief
website: https://www.geldersarchief.nl/
+web_enrichment:
+ web_archives:
+ - url: http://www.streekmuseumtiel.nl
+ directory: web/0155/streekmuseumtiel.nl
+ archive_timestamp: '2025-12-05T14:32:29.509627+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:33:04.077036+00:00'
diff --git a/data/nde/enriched/entries/1025_unknown.yaml b/data/nde/enriched/entries/1025_unknown.yaml
index b3d14b688a..f487c16844 100644
--- a/data/nde/enriched/entries/1025_unknown.yaml
+++ b/data/nde/enriched/entries/1025_unknown.yaml
@@ -1303,3 +1303,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:21:46.671527+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.geheugenvanzeist.nl/
+ directory: web/1025/geheugenvanzeist.nl
+ archive_timestamp: '2025-12-05T14:33:05.303247+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:33:11.066177+00:00'
diff --git a/data/nde/enriched/entries/1034_unknown.yaml b/data/nde/enriched/entries/1034_unknown.yaml
index a524d6e441..5c2a05e5be 100644
--- a/data/nde/enriched/entries/1034_unknown.yaml
+++ b/data/nde/enriched/entries/1034_unknown.yaml
@@ -4190,3 +4190,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:21:49.731484+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.historischekringbreukelen.nl/
+ directory: web/1034/historischekringbreukelen.nl
+ archive_timestamp: '2025-12-05T14:33:12.261710+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:33:16.150951+00:00'
diff --git a/data/nde/enriched/entries/1042_Q572269.yaml b/data/nde/enriched/entries/1042_Q572269.yaml
index b9329404f2..84fbb76354 100644
--- a/data/nde/enriched/entries/1042_Q572269.yaml
+++ b/data/nde/enriched/entries/1042_Q572269.yaml
@@ -2560,3 +2560,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:21:52.916432+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.kasteelamerongen.nl/
+ directory: web/1042/kasteelamerongen.nl
+ archive_timestamp: '2025-12-05T14:33:17.341524+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:33:20.893895+00:00'
diff --git a/data/nde/enriched/entries/1050_Q28058453.yaml b/data/nde/enriched/entries/1050_Q28058453.yaml
index 65d04a79ea..ec6ddb6e0b 100644
--- a/data/nde/enriched/entries/1050_Q28058453.yaml
+++ b/data/nde/enriched/entries/1050_Q28058453.yaml
@@ -5286,3 +5286,10 @@ youtube_enrichment:
comments_fetched: 0
videos_count: 77
status: SUCCESS
+web_enrichment:
+ web_archives:
+ - url: http://www.museumijsselstein.nl
+ directory: web/1050/museumijsselstein.nl
+ archive_timestamp: '2025-12-05T14:33:52.296668+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:33:54.863276+00:00'
diff --git a/data/nde/enriched/entries/1053_Q28956940.yaml b/data/nde/enriched/entries/1053_Q28956940.yaml
index 626bfc3e7e..786b2cbfdf 100644
--- a/data/nde/enriched/entries/1053_Q28956940.yaml
+++ b/data/nde/enriched/entries/1053_Q28956940.yaml
@@ -2380,3 +2380,10 @@ genealogiewerkbalk_enrichment:
name: Het Utrechts Archief
website: https://hetutrechtsarchief.nl/
extra_info: Kijk voor meer info over archieven in Utrecht op https://www.landschaperfgoedutrecht.nl/erfgoed/historische-verenigingen-en-archieven/archieven/
+web_enrichment:
+ web_archives:
+ - url: http://www.moa.nl/
+ directory: web/1053/moa.nl
+ archive_timestamp: '2025-12-05T14:33:56.054522+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:34:00.240692+00:00'
diff --git a/data/nde/enriched/entries/1055_Q1624224.yaml b/data/nde/enriched/entries/1055_Q1624224.yaml
index cad6832500..9e712042c9 100644
--- a/data/nde/enriched/entries/1055_Q1624224.yaml
+++ b/data/nde/enriched/entries/1055_Q1624224.yaml
@@ -7416,3 +7416,22 @@ youtube_enrichment:
comments_fetched: 8
videos_count: 105
status: SUCCESS
+web_enrichment:
+ web_archives:
+ - url: https://www.museumspeelklok.nl/
+ directory: web/1055/museumspeelklok.nl
+ archive_timestamp: '2025-12-05T14:34:01.514164+00:00'
+ status: new
+ - url: https://www.facebook.com/MuseumSpeelklok
+ directory: web/1055/facebook.com
+ archive_timestamp: '2025-12-05T14:34:04.054193+00:00'
+ status: new
+ - url: https://www.instagram.com/museumspeelklok
+ directory: web/1055/instagram.com
+ archive_timestamp: '2025-12-05T14:34:37.756009+00:00'
+ status: new
+ - url: https://www.youtube.com/channel/UCXv_fLzzL7UBnZtRG3A2QLw
+ directory: web/1055/youtube.com
+ archive_timestamp: '2025-12-05T14:34:43.963205+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:34:46.394677+00:00'
diff --git a/data/nde/enriched/entries/1058_Q2361897.yaml b/data/nde/enriched/entries/1058_Q2361897.yaml
index ac28412304..df59fc3d73 100644
--- a/data/nde/enriched/entries/1058_Q2361897.yaml
+++ b/data/nde/enriched/entries/1058_Q2361897.yaml
@@ -1583,3 +1583,10 @@ genealogiewerkbalk_enrichment:
name: Het Utrechts Archief
website: https://hetutrechtsarchief.nl/
extra_info: Kijk voor meer info over archieven in Utrecht op https://www.landschaperfgoedutrecht.nl/erfgoed/historische-verenigingen-en-archieven/archieven/
+web_enrichment:
+ web_archives:
+ - url: https://www.museumwarsenhoeck.nl
+ directory: web/1058/museumwarsenhoeck.nl
+ archive_timestamp: '2025-12-05T14:34:47.599048+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:34:54.502374+00:00'
diff --git a/data/nde/enriched/entries/1412_kb_isil.yaml b/data/nde/enriched/entries/1412_kb_isil.yaml
index 7a72584931..ef926eb9bd 100644
--- a/data/nde/enriched/entries/1412_kb_isil.yaml
+++ b/data/nde/enriched/entries/1412_kb_isil.yaml
@@ -320,6 +320,12 @@ web_enrichment:
source_type: official_website
fetch_status: SUCCESS
web_enrichment_status: SUCCESS
+ web_archives:
+ - url: https://bibliotheeknieuwegein.nl/
+ directory: web/1412/bibliotheeknieuwegein.nl
+ archive_timestamp: '2025-12-05T14:34:55.655669+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:34:59.179865+00:00'
ghcid:
ghcid_current: NL-UT-NIE-L-BN
ghcid_original: NL-UT-NIE-L-BN
diff --git a/data/nde/enriched/entries/1417_kb_isil.yaml b/data/nde/enriched/entries/1417_kb_isil.yaml
index 6cd1adb528..6256e82770 100644
--- a/data/nde/enriched/entries/1417_kb_isil.yaml
+++ b/data/nde/enriched/entries/1417_kb_isil.yaml
@@ -358,6 +358,12 @@ web_enrichment:
source_type: official_website
fetch_status: SUCCESS
web_enrichment_status: SUCCESS
+ web_archives:
+ - url: http://bibliotheekaandevliet.nl/
+ directory: web/1417/bibliotheekaandevliet.nl
+ archive_timestamp: '2025-12-05T14:35:00.528734+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:35:02.996549+00:00'
ghcid:
ghcid_current: NL-ZH-VOO-L-BV
ghcid_original: NL-ZH-VOO-L-BV
diff --git a/data/nde/enriched/entries/1424_kb_isil.yaml b/data/nde/enriched/entries/1424_kb_isil.yaml
index f75e0234f7..d96ff7377a 100644
--- a/data/nde/enriched/entries/1424_kb_isil.yaml
+++ b/data/nde/enriched/entries/1424_kb_isil.yaml
@@ -309,6 +309,12 @@ web_enrichment:
source_type: official_website
fetch_status: SUCCESS
web_enrichment_status: SUCCESS
+ web_archives:
+ - url: http://www.bibliotheek-zoetermeer.nl/
+ directory: web/1424/bibliotheek-zoetermeer.nl
+ archive_timestamp: '2025-12-05T14:35:04.108336+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:35:06.500865+00:00'
wikidata_enrichment:
wikidata_entity_id: Q59962036
wikidata_label: Bibliotheek Zoetermeer
diff --git a/data/nde/enriched/entries/1427_kb_isil.yaml b/data/nde/enriched/entries/1427_kb_isil.yaml
index fb3fa1e770..314c614b9b 100644
--- a/data/nde/enriched/entries/1427_kb_isil.yaml
+++ b/data/nde/enriched/entries/1427_kb_isil.yaml
@@ -288,6 +288,12 @@ web_enrichment:
source_type: official_website
fetch_status: SUCCESS
web_enrichment_status: SUCCESS
+ web_archives:
+ - url: https://www.facet-emmen.nl/
+ directory: web/1427/facet-emmen.nl
+ archive_timestamp: '2025-12-05T14:35:07.649942+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:35:10.044040+00:00'
ghcid:
ghcid_current: NL-DR-EMM-L-FEC
ghcid_original: NL-DR-EMM-L-FEC
diff --git a/data/nde/enriched/entries/1430_kb_isil.yaml b/data/nde/enriched/entries/1430_kb_isil.yaml
index beb9334191..241a6ef0c6 100644
--- a/data/nde/enriched/entries/1430_kb_isil.yaml
+++ b/data/nde/enriched/entries/1430_kb_isil.yaml
@@ -326,6 +326,12 @@ web_enrichment:
source_type: official_website
fetch_status: SUCCESS
web_enrichment_status: SUCCESS
+ web_archives:
+ - url: http://www.bibliotheekrivierenland.nl/
+ directory: web/1430/bibliotheekrivierenland.nl
+ archive_timestamp: '2025-12-05T14:35:11.229159+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:35:13.623938+00:00'
ghcid:
ghcid_current: NL-GE-TIE-L-BT
ghcid_original: NL-GE-TIE-L-BT
diff --git a/data/nde/enriched/entries/1550_feyenoord_museum.yaml b/data/nde/enriched/entries/1550_feyenoord_museum.yaml
index a5097f326d..4ea274a0b6 100644
--- a/data/nde/enriched/entries/1550_feyenoord_museum.yaml
+++ b/data/nde/enriched/entries/1550_feyenoord_museum.yaml
@@ -271,3 +271,10 @@ digital_platforms:
sustainability_model: Registered museum (government supported)
enrichment_timestamp: '2025-12-05T11:36:15.080625+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.dekuip.com/nl/tour-en-museum/arrangementen/feyenoord-museum
+ directory: web/1550/dekuip.com
+ archive_timestamp: '2025-12-05T14:35:47.052219+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:35:50.285727+00:00'
diff --git a/data/nde/enriched/entries/1573_vrijmetselarij_museum.yaml b/data/nde/enriched/entries/1573_vrijmetselarij_museum.yaml
index fa184e6152..a0613b2183 100644
--- a/data/nde/enriched/entries/1573_vrijmetselarij_museum.yaml
+++ b/data/nde/enriched/entries/1573_vrijmetselarij_museum.yaml
@@ -260,3 +260,10 @@ digital_platforms:
sustainability_model: Registered museum (government supported)
enrichment_timestamp: '2025-12-05T11:41:07.905206+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.vrijmetselarijmuseum.nl/
+ directory: web/1573/vrijmetselarijmuseum.nl
+ archive_timestamp: '2025-12-05T14:43:59.666353+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:44:03.727959+00:00'
diff --git a/data/nde/enriched/entries/1629_naturalis.yaml b/data/nde/enriched/entries/1629_naturalis.yaml
index bf4d3f5a05..c607730975 100644
--- a/data/nde/enriched/entries/1629_naturalis.yaml
+++ b/data/nde/enriched/entries/1629_naturalis.yaml
@@ -277,3 +277,10 @@ digital_platforms:
sustainability_model: Registered museum (government supported)
enrichment_timestamp: '2025-12-05T11:36:10.809001+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.naturalis.nl/
+ directory: web/1629/naturalis.nl
+ archive_timestamp: '2025-12-05T14:37:23.459286+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:37:27.465192+00:00'
diff --git a/data/nde/enriched/entries/1646_kuiperij.yaml b/data/nde/enriched/entries/1646_kuiperij.yaml
index f5b1d7ebe2..313b7294d6 100644
--- a/data/nde/enriched/entries/1646_kuiperij.yaml
+++ b/data/nde/enriched/entries/1646_kuiperij.yaml
@@ -249,3 +249,10 @@ digital_platforms:
sustainability_model: Registered museum (government supported)
enrichment_timestamp: '2025-12-05T11:40:55.858520+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://zaansmuseum.nl/zien-doen/kuiperij/
+ directory: web/1646/zaansmuseum.nl
+ archive_timestamp: '2025-12-05T14:37:28.485823+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:37:32.410552+00:00'
diff --git a/data/nde/enriched/entries/1657_heemkring_glatbeke.yaml b/data/nde/enriched/entries/1657_heemkring_glatbeke.yaml
index 680f7ab6d4..b9e3ae3e3c 100644
--- a/data/nde/enriched/entries/1657_heemkring_glatbeke.yaml
+++ b/data/nde/enriched/entries/1657_heemkring_glatbeke.yaml
@@ -155,3 +155,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.755561+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.beeldbankglatbeke.be
+ directory: web/1657/beeldbankglatbeke.be
+ archive_timestamp: '2025-12-05T14:38:04.488637+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:08.714618+00:00'
diff --git a/data/nde/enriched/entries/1659_historische_werkgroep_kynhout.yaml b/data/nde/enriched/entries/1659_historische_werkgroep_kynhout.yaml
index b65ae79891..000d3592af 100644
--- a/data/nde/enriched/entries/1659_historische_werkgroep_kynhout.yaml
+++ b/data/nde/enriched/entries/1659_historische_werkgroep_kynhout.yaml
@@ -180,3 +180,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:33.975109+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.beeldbankdeknipe.nl
+ directory: web/1659/beeldbankdeknipe.nl
+ archive_timestamp: '2025-12-05T14:38:09.812120+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:15.377654+00:00'
diff --git a/data/nde/enriched/entries/1665_heemkring_de_reengenoten.yaml b/data/nde/enriched/entries/1665_heemkring_de_reengenoten.yaml
index fa3a2c7339..d7536860e0 100644
--- a/data/nde/enriched/entries/1665_heemkring_de_reengenoten.yaml
+++ b/data/nde/enriched/entries/1665_heemkring_de_reengenoten.yaml
@@ -157,3 +157,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:46.188133+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.archiefdereengenoten.be
+ directory: web/1665/archiefdereengenoten.be
+ archive_timestamp: '2025-12-05T14:38:16.403729+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:20.239267+00:00'
diff --git a/data/nde/enriched/entries/1668_heemkundige_kring_wissekerke.yaml b/data/nde/enriched/entries/1668_heemkundige_kring_wissekerke.yaml
index 1fad430a73..0842bbf6b1 100644
--- a/data/nde/enriched/entries/1668_heemkundige_kring_wissekerke.yaml
+++ b/data/nde/enriched/entries/1668_heemkundige_kring_wissekerke.yaml
@@ -195,3 +195,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:30.338001+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://collectie.wissekerke.be
+ directory: web/1668/collectie.wissekerke.be
+ archive_timestamp: '2025-12-05T14:38:21.262490+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:24.888517+00:00'
diff --git a/data/nde/enriched/entries/1675_stichting_splika.yaml b/data/nde/enriched/entries/1675_stichting_splika.yaml
index 6d63e85462..35e7938a19 100644
--- a/data/nde/enriched/entries/1675_stichting_splika.yaml
+++ b/data/nde/enriched/entries/1675_stichting_splika.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:41:06.003139+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.splika.nl
+ directory: web/1675/splika.nl
+ archive_timestamp: '2025-12-05T14:38:26.195369+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:32.234249+00:00'
diff --git a/data/nde/enriched/entries/1677_1_april_vereniging.yaml b/data/nde/enriched/entries/1677_1_april_vereniging.yaml
index e74a20defc..525c2c3228 100644
--- a/data/nde/enriched/entries/1677_1_april_vereniging.yaml
+++ b/data/nde/enriched/entries/1677_1_april_vereniging.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:22.690549+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.1aprilvereniging.nl
+ directory: web/1677/1aprilvereniging.nl
+ archive_timestamp: '2025-12-05T14:38:33.254393+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:37.048466+00:00'
diff --git a/data/nde/enriched/entries/1680_arresleeclub_glijen_en_rijen.yaml b/data/nde/enriched/entries/1680_arresleeclub_glijen_en_rijen.yaml
index 0e5a4c27f2..983fd7f3a4 100644
--- a/data/nde/enriched/entries/1680_arresleeclub_glijen_en_rijen.yaml
+++ b/data/nde/enriched/entries/1680_arresleeclub_glijen_en_rijen.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:41:46.106385+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.glijenenrijen.nl
+ directory: web/1680/glijenenrijen.nl
+ archive_timestamp: '2025-12-05T14:38:38.160074+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:44.995795+00:00'
diff --git a/data/nde/enriched/entries/1682_bakkerij_schabbink.yaml b/data/nde/enriched/entries/1682_bakkerij_schabbink.yaml
index b41c75761b..8e87d7cbe6 100644
--- a/data/nde/enriched/entries/1682_bakkerij_schabbink.yaml
+++ b/data/nde/enriched/entries/1682_bakkerij_schabbink.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:38.281424+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.bakkerijschabbink.nl
+ directory: web/1682/bakkerijschabbink.nl
+ archive_timestamp: '2025-12-05T14:38:46.014092+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:49.270077+00:00'
diff --git a/data/nde/enriched/entries/1683_bakkerij_van_ooijen.yaml b/data/nde/enriched/entries/1683_bakkerij_van_ooijen.yaml
index b83cf749c9..9cbb7589da 100644
--- a/data/nde/enriched/entries/1683_bakkerij_van_ooijen.yaml
+++ b/data/nde/enriched/entries/1683_bakkerij_van_ooijen.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:09.689689+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.bakkerijvanooijen.nl
+ directory: web/1683/bakkerijvanooijen.nl
+ archive_timestamp: '2025-12-05T14:38:50.290931+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:54.228293+00:00'
diff --git a/data/nde/enriched/entries/1684_bakkerij_van_der_most.yaml b/data/nde/enriched/entries/1684_bakkerij_van_der_most.yaml
index 9d1366c223..0d345c25ba 100644
--- a/data/nde/enriched/entries/1684_bakkerij_van_der_most.yaml
+++ b/data/nde/enriched/entries/1684_bakkerij_van_der_most.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:20.068798+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.bakkerijvandermost.nl
+ directory: web/1684/bakkerijvandermost.nl
+ archive_timestamp: '2025-12-05T14:38:55.257366+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:38:58.548894+00:00'
diff --git a/data/nde/enriched/entries/1686_berry_rutjes_jr_hoedenontwerper.yaml b/data/nde/enriched/entries/1686_berry_rutjes_jr_hoedenontwerper.yaml
index 660156f06d..96863031dc 100644
--- a/data/nde/enriched/entries/1686_berry_rutjes_jr_hoedenontwerper.yaml
+++ b/data/nde/enriched/entries/1686_berry_rutjes_jr_hoedenontwerper.yaml
@@ -122,3 +122,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:09.702767+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.berryrutjes.com
+ directory: web/1686/berryrutjes.com
+ archive_timestamp: '2025-12-05T14:38:59.685679+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:10.034829+00:00'
diff --git a/data/nde/enriched/entries/1689_bond_friese_vogelwachten_bfvw.yaml b/data/nde/enriched/entries/1689_bond_friese_vogelwachten_bfvw.yaml
index cb1b54852e..593ec5253b 100644
--- a/data/nde/enriched/entries/1689_bond_friese_vogelwachten_bfvw.yaml
+++ b/data/nde/enriched/entries/1689_bond_friese_vogelwachten_bfvw.yaml
@@ -115,3 +115,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:13.570037+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.friesevogelwachten.nl
+ directory: web/1689/friesevogelwachten.nl
+ archive_timestamp: '2025-12-05T14:39:11.057413+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:17.596184+00:00'
diff --git a/data/nde/enriched/entries/1691_brabantse_orgelfederatie.yaml b/data/nde/enriched/entries/1691_brabantse_orgelfederatie.yaml
index 880897ffde..c23c52f01d 100644
--- a/data/nde/enriched/entries/1691_brabantse_orgelfederatie.yaml
+++ b/data/nde/enriched/entries/1691_brabantse_orgelfederatie.yaml
@@ -119,3 +119,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:38.297569+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.brabantorgel.nl
+ directory: web/1691/brabantorgel.nl
+ archive_timestamp: '2025-12-05T14:39:18.648981+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:21.957942+00:00'
diff --git a/data/nde/enriched/entries/1692_broederschap_van_onze_lieve_vrouw_sterre_der_zee.yaml b/data/nde/enriched/entries/1692_broederschap_van_onze_lieve_vrouw_sterre_der_zee.yaml
index 53b03382f1..da8e6f5c42 100644
--- a/data/nde/enriched/entries/1692_broederschap_van_onze_lieve_vrouw_sterre_der_zee.yaml
+++ b/data/nde/enriched/entries/1692_broederschap_van_onze_lieve_vrouw_sterre_der_zee.yaml
@@ -118,3 +118,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:45.028691+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://olv-bidweg.nl/
+ directory: web/1692/olv-bidweg.nl
+ archive_timestamp: '2025-12-05T14:39:22.970244+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:26.078453+00:00'
diff --git a/data/nde/enriched/entries/1693_buurt_ede_en_veldhuizen.yaml b/data/nde/enriched/entries/1693_buurt_ede_en_veldhuizen.yaml
index 367436f257..03be6d726f 100644
--- a/data/nde/enriched/entries/1693_buurt_ede_en_veldhuizen.yaml
+++ b/data/nde/enriched/entries/1693_buurt_ede_en_veldhuizen.yaml
@@ -119,3 +119,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:34.192548+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://buurt.ede-en-veldhuizen.nl
+ directory: web/1693/buurt.ede-en-veldhuizen.nl
+ archive_timestamp: '2025-12-05T14:39:27.092969+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:33.540456+00:00'
diff --git a/data/nde/enriched/entries/1695_carnavalsvereniging_de_eileuvers.yaml b/data/nde/enriched/entries/1695_carnavalsvereniging_de_eileuvers.yaml
index a3966ca463..18aa5dd681 100644
--- a/data/nde/enriched/entries/1695_carnavalsvereniging_de_eileuvers.yaml
+++ b/data/nde/enriched/entries/1695_carnavalsvereniging_de_eileuvers.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:29.113191+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://eileuvers.nl/
+ directory: web/1695/eileuvers.nl
+ archive_timestamp: '2025-12-05T14:39:35.281414+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:40.670458+00:00'
diff --git a/data/nde/enriched/entries/1697_comité_tot_instandhouding_van_neerlands_oudste_paa.yaml b/data/nde/enriched/entries/1697_comité_tot_instandhouding_van_neerlands_oudste_paa.yaml
index abfdaa027e..85dff0dd73 100644
--- a/data/nde/enriched/entries/1697_comité_tot_instandhouding_van_neerlands_oudste_paa.yaml
+++ b/data/nde/enriched/entries/1697_comité_tot_instandhouding_van_neerlands_oudste_paa.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.733749+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.demart.nl
+ directory: web/1697/demart.nl
+ archive_timestamp: '2025-12-05T14:39:41.686264+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:44.396214+00:00'
diff --git a/data/nde/enriched/entries/1698_commissie_uit_de_ingezetenen_van_de_afdeling_orthe.yaml b/data/nde/enriched/entries/1698_commissie_uit_de_ingezetenen_van_de_afdeling_orthe.yaml
index b7db24c3c3..4070b1d878 100644
--- a/data/nde/enriched/entries/1698_commissie_uit_de_ingezetenen_van_de_afdeling_orthe.yaml
+++ b/data/nde/enriched/entries/1698_commissie_uit_de_ingezetenen_van_de_afdeling_orthe.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:32.890803+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://orthen.nl/commissie/
+ directory: web/1698/orthen.nl
+ archive_timestamp: '2025-12-05T14:39:45.407911+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:49.057272+00:00'
diff --git a/data/nde/enriched/entries/1702_de_stoelenmatter.yaml b/data/nde/enriched/entries/1702_de_stoelenmatter.yaml
index fb50843b86..708413087a 100644
--- a/data/nde/enriched/entries/1702_de_stoelenmatter.yaml
+++ b/data/nde/enriched/entries/1702_de_stoelenmatter.yaml
@@ -115,3 +115,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.775412+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.destoelenmatter.nl
+ directory: web/1702/destoelenmatter.nl
+ archive_timestamp: '2025-12-05T14:39:50.071547+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:52.907427+00:00'
diff --git a/data/nde/enriched/entries/1704_diepenheimse_schutterij.yaml b/data/nde/enriched/entries/1704_diepenheimse_schutterij.yaml
index 32b063ad93..c971990daf 100644
--- a/data/nde/enriched/entries/1704_diepenheimse_schutterij.yaml
+++ b/data/nde/enriched/entries/1704_diepenheimse_schutterij.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:16.561612+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.diepenheimseschutterij.nl
+ directory: web/1704/diepenheimseschutterij.nl
+ archive_timestamp: '2025-12-05T14:39:53.923065+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:39:57.831323+00:00'
diff --git a/data/nde/enriched/entries/1707_erfgoed_platform_schouwen_duiveland.yaml b/data/nde/enriched/entries/1707_erfgoed_platform_schouwen_duiveland.yaml
index a6b72ff40e..7275d95c2b 100644
--- a/data/nde/enriched/entries/1707_erfgoed_platform_schouwen_duiveland.yaml
+++ b/data/nde/enriched/entries/1707_erfgoed_platform_schouwen_duiveland.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:49.771448+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://erfgoedschouwenduiveland.nl/
+ directory: web/1707/erfgoedschouwenduiveland.nl
+ archive_timestamp: '2025-12-05T14:39:58.849007+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:01.304507+00:00'
diff --git a/data/nde/enriched/entries/1711_floralia_corso_frederiksoord_eo.yaml b/data/nde/enriched/entries/1711_floralia_corso_frederiksoord_eo.yaml
index eef6bf11f9..13daf8fbbb 100644
--- a/data/nde/enriched/entries/1711_floralia_corso_frederiksoord_eo.yaml
+++ b/data/nde/enriched/entries/1711_floralia_corso_frederiksoord_eo.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:44.513474+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.corsofrederiksoord.nl
+ directory: web/1711/corsofrederiksoord.nl
+ archive_timestamp: '2025-12-05T14:40:02.470166+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:09.113022+00:00'
diff --git a/data/nde/enriched/entries/1716_gilde_st_jan_baptista_leenderstrijp.yaml b/data/nde/enriched/entries/1716_gilde_st_jan_baptista_leenderstrijp.yaml
index 271574a9bb..67ee4ba91a 100644
--- a/data/nde/enriched/entries/1716_gilde_st_jan_baptista_leenderstrijp.yaml
+++ b/data/nde/enriched/entries/1716_gilde_st_jan_baptista_leenderstrijp.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:21.510530+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.gildeleenderstrijp.nl
+ directory: web/1716/gildeleenderstrijp.nl
+ archive_timestamp: '2025-12-05T14:40:10.127152+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:24.890830+00:00'
diff --git a/data/nde/enriched/entries/1717_goede_doelen_nederland.yaml b/data/nde/enriched/entries/1717_goede_doelen_nederland.yaml
index a3e9987bb1..ebbb0b9501 100644
--- a/data/nde/enriched/entries/1717_goede_doelen_nederland.yaml
+++ b/data/nde/enriched/entries/1717_goede_doelen_nederland.yaml
@@ -118,3 +118,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:41:03.410925+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.goededoelennederland.nl
+ directory: web/1717/goededoelennederland.nl
+ archive_timestamp: '2025-12-05T14:40:25.911051+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:29.087560+00:00'
diff --git a/data/nde/enriched/entries/1718_haagse_tilduivenbond_ons_belang.yaml b/data/nde/enriched/entries/1718_haagse_tilduivenbond_ons_belang.yaml
index 2f2d094512..fe84514abe 100644
--- a/data/nde/enriched/entries/1718_haagse_tilduivenbond_ons_belang.yaml
+++ b/data/nde/enriched/entries/1718_haagse_tilduivenbond_ons_belang.yaml
@@ -118,3 +118,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:43.469305+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.tilduivenbondonsbelang.nl
+ directory: web/1718/tilduivenbondonsbelang.nl
+ archive_timestamp: '2025-12-05T14:40:30.102715+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:37.066148+00:00'
diff --git a/data/nde/enriched/entries/1719_harddraverij_vereniging_assendelft.yaml b/data/nde/enriched/entries/1719_harddraverij_vereniging_assendelft.yaml
index c4c52127c3..03a659c666 100644
--- a/data/nde/enriched/entries/1719_harddraverij_vereniging_assendelft.yaml
+++ b/data/nde/enriched/entries/1719_harddraverij_vereniging_assendelft.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:30.577510+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.harddraverijassendelft.nl
+ directory: web/1719/harddraverijassendelft.nl
+ archive_timestamp: '2025-12-05T14:40:38.082788+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:41.308516+00:00'
diff --git a/data/nde/enriched/entries/1720_harddraverij_vereniging_santpoort_en_omstreken.yaml b/data/nde/enriched/entries/1720_harddraverij_vereniging_santpoort_en_omstreken.yaml
index 9aeb02175f..12f8a63a56 100644
--- a/data/nde/enriched/entries/1720_harddraverij_vereniging_santpoort_en_omstreken.yaml
+++ b/data/nde/enriched/entries/1720_harddraverij_vereniging_santpoort_en_omstreken.yaml
@@ -116,3 +116,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:48.273382+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.dorpsfeest-santpoort.nl
+ directory: web/1720/dorpsfeest-santpoort.nl
+ archive_timestamp: '2025-12-05T14:40:42.325602+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:45.524111+00:00'
diff --git a/data/nde/enriched/entries/1721_harddraverijvereniging_heemskerk.yaml b/data/nde/enriched/entries/1721_harddraverijvereniging_heemskerk.yaml
index e7fd7f9725..5d09e188c9 100644
--- a/data/nde/enriched/entries/1721_harddraverijvereniging_heemskerk.yaml
+++ b/data/nde/enriched/entries/1721_harddraverijvereniging_heemskerk.yaml
@@ -112,3 +112,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:51.378958+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://harddraverijheemskerk.nl
+ directory: web/1721/harddraverijheemskerk.nl
+ archive_timestamp: '2025-12-05T14:40:46.540310+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:49.846479+00:00'
diff --git a/data/nde/enriched/entries/1722_harddraverijvereniging_hillegom_en_omstreken.yaml b/data/nde/enriched/entries/1722_harddraverijvereniging_hillegom_en_omstreken.yaml
index b6b799205f..824fae2257 100644
--- a/data/nde/enriched/entries/1722_harddraverijvereniging_hillegom_en_omstreken.yaml
+++ b/data/nde/enriched/entries/1722_harddraverijvereniging_hillegom_en_omstreken.yaml
@@ -113,3 +113,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:38.642594+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://harddraverijvereniginghillegom.nl
+ directory: web/1722/harddraverijvereniginghillegom.nl
+ archive_timestamp: '2025-12-05T14:40:50.859123+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:40:54.846891+00:00'
diff --git a/data/nde/enriched/entries/1725_haw_ut_hellemonds.yaml b/data/nde/enriched/entries/1725_haw_ut_hellemonds.yaml
index d2091f11ac..842d804405 100644
--- a/data/nde/enriched/entries/1725_haw_ut_hellemonds.yaml
+++ b/data/nde/enriched/entries/1725_haw_ut_hellemonds.yaml
@@ -133,3 +133,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:15.627843+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://hawuthellemonds.nl
+ directory: web/1725/hawuthellemonds.nl
+ archive_timestamp: '2025-12-05T14:40:55.864126+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:41:00.199970+00:00'
diff --git a/data/nde/enriched/entries/1728_het_schuttersgilde.yaml b/data/nde/enriched/entries/1728_het_schuttersgilde.yaml
index 3fd21c48a7..9de2939865 100644
--- a/data/nde/enriched/entries/1728_het_schuttersgilde.yaml
+++ b/data/nde/enriched/entries/1728_het_schuttersgilde.yaml
@@ -120,3 +120,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:03.121155+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://schuttersgilde-kampen.nl/
+ directory: web/1728/schuttersgilde-kampen.nl
+ archive_timestamp: '2025-12-05T14:45:38.548703+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:45:45.223491+00:00'
diff --git a/data/nde/enriched/entries/1729_istimewa_events.yaml b/data/nde/enriched/entries/1729_istimewa_events.yaml
index 26b7611276..d2bc3a9919 100644
--- a/data/nde/enriched/entries/1729_istimewa_events.yaml
+++ b/data/nde/enriched/entries/1729_istimewa_events.yaml
@@ -122,3 +122,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:42.353670+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.istimewa-events.nl
+ directory: web/1729/istimewa-events.nl
+ archive_timestamp: '2025-12-05T14:45:46.237345+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:45:50.565089+00:00'
diff --git a/data/nde/enriched/entries/1731_in_honorem_dei.yaml b/data/nde/enriched/entries/1731_in_honorem_dei.yaml
index 029498120e..12c01f04c6 100644
--- a/data/nde/enriched/entries/1731_in_honorem_dei.yaml
+++ b/data/nde/enriched/entries/1731_in_honorem_dei.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:25.035632+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://in-honorem-dei.org/
+ directory: web/1731/in-honorem-dei.org
+ archive_timestamp: '2025-12-05T14:45:51.581329+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:45:55.580476+00:00'
diff --git a/data/nde/enriched/entries/1733_jonkheid_banholt.yaml b/data/nde/enriched/entries/1733_jonkheid_banholt.yaml
index 5ece7f3b05..0f36eaf96f 100644
--- a/data/nde/enriched/entries/1733_jonkheid_banholt.yaml
+++ b/data/nde/enriched/entries/1733_jonkheid_banholt.yaml
@@ -126,3 +126,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.389174+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.jonkheid-banholt.nl
+ directory: web/1733/jonkheid-banholt.nl
+ archive_timestamp: '2025-12-05T14:45:56.596594+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:45:59.253200+00:00'
diff --git a/data/nde/enriched/entries/1734_jonkheid_sancta_brigida_te_noorbeek.yaml b/data/nde/enriched/entries/1734_jonkheid_sancta_brigida_te_noorbeek.yaml
index 7207e7e8ba..42a39f07a7 100644
--- a/data/nde/enriched/entries/1734_jonkheid_sancta_brigida_te_noorbeek.yaml
+++ b/data/nde/enriched/entries/1734_jonkheid_sancta_brigida_te_noorbeek.yaml
@@ -127,3 +127,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:38.771970+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.jonkheidnoorbeek.nl
+ directory: web/1734/jonkheidnoorbeek.nl
+ archive_timestamp: '2025-12-05T14:46:00.271015+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:06.107035+00:00'
diff --git a/data/nde/enriched/entries/1735_knjv.yaml b/data/nde/enriched/entries/1735_knjv.yaml
index 505e06b3b8..0c9b570331 100644
--- a/data/nde/enriched/entries/1735_knjv.yaml
+++ b/data/nde/enriched/entries/1735_knjv.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:11.651401+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://knjv.com/
+ directory: web/1735/knjv.com
+ archive_timestamp: '2025-12-05T14:46:07.125079+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:10.692957+00:00'
diff --git a/data/nde/enriched/entries/1737_knsb.yaml b/data/nde/enriched/entries/1737_knsb.yaml
index c042e8e2c9..467df16c36 100644
--- a/data/nde/enriched/entries/1737_knsb.yaml
+++ b/data/nde/enriched/entries/1737_knsb.yaml
@@ -122,3 +122,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:15.084691+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.knsb.nl
+ directory: web/1737/knsb.nl
+ archive_timestamp: '2025-12-05T14:46:11.816593+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:15.444707+00:00'
diff --git a/data/nde/enriched/entries/1739_kermis_oranjevereniging_haarzuilens.yaml b/data/nde/enriched/entries/1739_kermis_oranjevereniging_haarzuilens.yaml
index 50104048d2..851435490c 100644
--- a/data/nde/enriched/entries/1739_kermis_oranjevereniging_haarzuilens.yaml
+++ b/data/nde/enriched/entries/1739_kermis_oranjevereniging_haarzuilens.yaml
@@ -126,3 +126,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:27.202863+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.kovh.nl/
+ directory: web/1739/kovh.nl
+ archive_timestamp: '2025-12-05T14:46:16.557666+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:20.470573+00:00'
diff --git a/data/nde/enriched/entries/1740_koninklijke_nederlandsche_kolfbond.yaml b/data/nde/enriched/entries/1740_koninklijke_nederlandsche_kolfbond.yaml
index 0002d3395e..e101f8a2c8 100644
--- a/data/nde/enriched/entries/1740_koninklijke_nederlandsche_kolfbond.yaml
+++ b/data/nde/enriched/entries/1740_koninklijke_nederlandsche_kolfbond.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:11.639290+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://kolfbond.nl/
+ directory: web/1740/kolfbond.nl
+ archive_timestamp: '2025-12-05T14:46:21.492260+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:24.063185+00:00'
diff --git a/data/nde/enriched/entries/1741_koninklijke_nederlandse_studenten_roeibond.yaml b/data/nde/enriched/entries/1741_koninklijke_nederlandse_studenten_roeibond.yaml
index 6e79f1b2f7..aed35285c2 100644
--- a/data/nde/enriched/entries/1741_koninklijke_nederlandse_studenten_roeibond.yaml
+++ b/data/nde/enriched/entries/1741_koninklijke_nederlandse_studenten_roeibond.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:46.159618+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.varsity.nl
+ directory: web/1741/varsity.nl
+ archive_timestamp: '2025-12-05T14:46:25.076870+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:28.372699+00:00'
diff --git a/data/nde/enriched/entries/1742_koninklijke_vereeniging_voor_volksvermaken.yaml b/data/nde/enriched/entries/1742_koninklijke_vereeniging_voor_volksvermaken.yaml
index 7140400b11..909f18a492 100644
--- a/data/nde/enriched/entries/1742_koninklijke_vereeniging_voor_volksvermaken.yaml
+++ b/data/nde/enriched/entries/1742_koninklijke_vereeniging_voor_volksvermaken.yaml
@@ -120,3 +120,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:37.573585+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.volksvermakengroningen.nl
+ directory: web/1742/volksvermakengroningen.nl
+ archive_timestamp: '2025-12-05T14:46:29.385903+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:46:56.062464+00:00'
diff --git a/data/nde/enriched/entries/1743_kopro_beki_prodo.yaml b/data/nde/enriched/entries/1743_kopro_beki_prodo.yaml
index 933202dbcf..7ec69540dc 100644
--- a/data/nde/enriched/entries/1743_kopro_beki_prodo.yaml
+++ b/data/nde/enriched/entries/1743_kopro_beki_prodo.yaml
@@ -120,3 +120,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:52.599274+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.koprobekiprodo.wordpress.com
+ directory: web/1743/koprobekiprodo.wordpress.com
+ archive_timestamp: '2025-12-05T14:46:57.080503+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:00.304544+00:00'
diff --git a/data/nde/enriched/entries/1748_nardus_samenwerkende_uitvaartorganisaties.yaml b/data/nde/enriched/entries/1748_nardus_samenwerkende_uitvaartorganisaties.yaml
index 3ddb007b70..9412b6d6b0 100644
--- a/data/nde/enriched/entries/1748_nardus_samenwerkende_uitvaartorganisaties.yaml
+++ b/data/nde/enriched/entries/1748_nardus_samenwerkende_uitvaartorganisaties.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.370064+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.nardus.eu
+ directory: web/1748/nardus.eu
+ archive_timestamp: '2025-12-05T14:47:01.327271+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:07.596175+00:00'
diff --git a/data/nde/enriched/entries/1749_nationaal_comité_4_en_5_mei.yaml b/data/nde/enriched/entries/1749_nationaal_comité_4_en_5_mei.yaml
index 73511424ec..2b5a88c7fe 100644
--- a/data/nde/enriched/entries/1749_nationaal_comité_4_en_5_mei.yaml
+++ b/data/nde/enriched/entries/1749_nationaal_comité_4_en_5_mei.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:13.418400+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.4en5mei.nl
+ directory: web/1749/4en5mei.nl
+ archive_timestamp: '2025-12-05T14:47:08.622074+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:11.912818+00:00'
diff --git a/data/nde/enriched/entries/1750_nationale_oldtimerdag.yaml b/data/nde/enriched/entries/1750_nationale_oldtimerdag.yaml
index 0536f05969..a0c7045b21 100644
--- a/data/nde/enriched/entries/1750_nationale_oldtimerdag.yaml
+++ b/data/nde/enriched/entries/1750_nationale_oldtimerdag.yaml
@@ -134,3 +134,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:13.556717+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.nationaleoldtimerdag.nl
+ directory: web/1750/nationaleoldtimerdag.nl
+ archive_timestamp: '2025-12-05T14:47:12.929871+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:18.026840+00:00'
diff --git a/data/nde/enriched/entries/1751_nautische_jongeren_vereniging_de_haven.yaml b/data/nde/enriched/entries/1751_nautische_jongeren_vereniging_de_haven.yaml
index c95d7ab145..b3a0ae7af2 100644
--- a/data/nde/enriched/entries/1751_nautische_jongeren_vereniging_de_haven.yaml
+++ b/data/nde/enriched/entries/1751_nautische_jongeren_vereniging_de_haven.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:05.561405+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://haventje.nl/erfgoed/
+ directory: web/1751/haventje.nl
+ archive_timestamp: '2025-12-05T14:47:19.045653+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:23.058320+00:00'
diff --git a/data/nde/enriched/entries/1752_nederlands_genootschap_voor_heraldiek.yaml b/data/nde/enriched/entries/1752_nederlands_genootschap_voor_heraldiek.yaml
index f5b0725bdb..3880bf8546 100644
--- a/data/nde/enriched/entries/1752_nederlands_genootschap_voor_heraldiek.yaml
+++ b/data/nde/enriched/entries/1752_nederlands_genootschap_voor_heraldiek.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:12.350135+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://genootschap-heraldiek.nl/
+ directory: web/1752/genootschap-heraldiek.nl
+ archive_timestamp: '2025-12-05T14:47:24.077905+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:47:28.635879+00:00'
diff --git a/data/nde/enriched/entries/1754_nederlandse_beugel_bond.yaml b/data/nde/enriched/entries/1754_nederlandse_beugel_bond.yaml
index 9245bd558c..6b18bafc6a 100644
--- a/data/nde/enriched/entries/1754_nederlandse_beugel_bond.yaml
+++ b/data/nde/enriched/entries/1754_nederlandse_beugel_bond.yaml
@@ -124,3 +124,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:29.384799+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.beugelen.nl
+ directory: web/1754/beugelen.nl
+ archive_timestamp: '2025-12-05T14:47:59.750629+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:02.422149+00:00'
diff --git a/data/nde/enriched/entries/1756_nederlandse_carnavalsstichting_het_groot_gevolg.yaml b/data/nde/enriched/entries/1756_nederlandse_carnavalsstichting_het_groot_gevolg.yaml
index 350eaf737c..8d8e086438 100644
--- a/data/nde/enriched/entries/1756_nederlandse_carnavalsstichting_het_groot_gevolg.yaml
+++ b/data/nde/enriched/entries/1756_nederlandse_carnavalsstichting_het_groot_gevolg.yaml
@@ -128,3 +128,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:24.697423+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.hetgrootgevolg.nl/
+ directory: web/1756/hetgrootgevolg.nl
+ archive_timestamp: '2025-12-05T14:48:03.435689+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:06.305588+00:00'
diff --git a/data/nde/enriched/entries/1757_nederlandse_federatie_voor_pijprokers.yaml b/data/nde/enriched/entries/1757_nederlandse_federatie_voor_pijprokers.yaml
index be835e984c..d8c095755c 100644
--- a/data/nde/enriched/entries/1757_nederlandse_federatie_voor_pijprokers.yaml
+++ b/data/nde/enriched/entries/1757_nederlandse_federatie_voor_pijprokers.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:53.696804+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.pijprokers.nl
+ directory: web/1757/pijprokers.nl
+ archive_timestamp: '2025-12-05T14:48:07.319717+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:11.199979+00:00'
diff --git a/data/nde/enriched/entries/1759_nederlandse_pencak_silat_federatie.yaml b/data/nde/enriched/entries/1759_nederlandse_pencak_silat_federatie.yaml
index 838e19d571..9d984c0734 100644
--- a/data/nde/enriched/entries/1759_nederlandse_pencak_silat_federatie.yaml
+++ b/data/nde/enriched/entries/1759_nederlandse_pencak_silat_federatie.yaml
@@ -125,3 +125,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:30.324300+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.npsf.nl
+ directory: web/1759/npsf.nl
+ archive_timestamp: '2025-12-05T14:48:12.221821+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:17.545707+00:00'
diff --git a/data/nde/enriched/entries/1760_nederlandse_postduivenhouders_organisatie.yaml b/data/nde/enriched/entries/1760_nederlandse_postduivenhouders_organisatie.yaml
index 240e3c38a8..d84726f762 100644
--- a/data/nde/enriched/entries/1760_nederlandse_postduivenhouders_organisatie.yaml
+++ b/data/nde/enriched/entries/1760_nederlandse_postduivenhouders_organisatie.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:15.067672+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.duivensportbond.nl
+ directory: web/1760/duivensportbond.nl
+ archive_timestamp: '2025-12-05T14:48:18.560751+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:21.147401+00:00'
diff --git a/data/nde/enriched/entries/1761_nederlandse_vereniging_voor_papierknipkunst.yaml b/data/nde/enriched/entries/1761_nederlandse_vereniging_voor_papierknipkunst.yaml
index c5bba8513d..6f728c7498 100644
--- a/data/nde/enriched/entries/1761_nederlandse_vereniging_voor_papierknipkunst.yaml
+++ b/data/nde/enriched/entries/1761_nederlandse_vereniging_voor_papierknipkunst.yaml
@@ -120,3 +120,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:41:20.062948+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.papierknippen.nl
+ directory: web/1761/papierknippen.nl
+ archive_timestamp: '2025-12-05T14:48:22.164532+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:25.563905+00:00'
diff --git a/data/nde/enriched/entries/1763_noord_brabantse_federatie_van_schuttersgilden.yaml b/data/nde/enriched/entries/1763_noord_brabantse_federatie_van_schuttersgilden.yaml
index 3fe66d46b3..1e220cf283 100644
--- a/data/nde/enriched/entries/1763_noord_brabantse_federatie_van_schuttersgilden.yaml
+++ b/data/nde/enriched/entries/1763_noord_brabantse_federatie_van_schuttersgilden.yaml
@@ -130,3 +130,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:36.413794+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.nbfs.nl
+ directory: web/1763/nbfs.nl
+ archive_timestamp: '2025-12-05T14:48:27.405060+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:30.713069+00:00'
diff --git a/data/nde/enriched/entries/1764_ocv_de_kadolstermennekes.yaml b/data/nde/enriched/entries/1764_ocv_de_kadolstermennekes.yaml
index fcf51088f4..9a56a6eb73 100644
--- a/data/nde/enriched/entries/1764_ocv_de_kadolstermennekes.yaml
+++ b/data/nde/enriched/entries/1764_ocv_de_kadolstermennekes.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:35.002087+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.dekadolstermennekes.nl
+ directory: web/1764/dekadolstermennekes.nl
+ archive_timestamp: '2025-12-05T14:48:31.726720+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:38.709065+00:00'
diff --git a/data/nde/enriched/entries/1765_oald_heldern_de_noaberschop.yaml b/data/nde/enriched/entries/1765_oald_heldern_de_noaberschop.yaml
index 9b98d8f504..95148b3cd2 100644
--- a/data/nde/enriched/entries/1765_oald_heldern_de_noaberschop.yaml
+++ b/data/nde/enriched/entries/1765_oald_heldern_de_noaberschop.yaml
@@ -125,3 +125,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:07.161781+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.oaldheldern.nl
+ directory: web/1765/oaldheldern.nl
+ archive_timestamp: '2025-12-05T14:48:39.728008+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:43.523144+00:00'
diff --git a/data/nde/enriched/entries/1768_papiermakerij_doesburg.yaml b/data/nde/enriched/entries/1768_papiermakerij_doesburg.yaml
index 2c3d1bd9c7..1771ed151f 100644
--- a/data/nde/enriched/entries/1768_papiermakerij_doesburg.yaml
+++ b/data/nde/enriched/entries/1768_papiermakerij_doesburg.yaml
@@ -134,3 +134,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:05.537627+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://www.papiermakerij-doesburg.nl
+ directory: web/1768/papiermakerij-doesburg.nl
+ archive_timestamp: '2025-12-05T14:48:44.534895+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:48.877318+00:00'
diff --git a/data/nde/enriched/entries/1769_papiermakerij_de_hoop.yaml b/data/nde/enriched/entries/1769_papiermakerij_de_hoop.yaml
index b63f25d916..3b0456d38a 100644
--- a/data/nde/enriched/entries/1769_papiermakerij_de_hoop.yaml
+++ b/data/nde/enriched/entries/1769_papiermakerij_de_hoop.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:41.137559+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.papiermakerijdehoop.nl
+ directory: web/1769/papiermakerijdehoop.nl
+ archive_timestamp: '2025-12-05T14:48:49.889038+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:48:54.919796+00:00'
diff --git a/data/nde/enriched/entries/1771_platform_handschriftontwikkeling.yaml b/data/nde/enriched/entries/1771_platform_handschriftontwikkeling.yaml
index ce46ab718b..994738c4bf 100644
--- a/data/nde/enriched/entries/1771_platform_handschriftontwikkeling.yaml
+++ b/data/nde/enriched/entries/1771_platform_handschriftontwikkeling.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:09.492435+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.handschriftontwikkeling.nl/
+ directory: web/1771/handschriftontwikkeling.nl
+ archive_timestamp: '2025-12-05T14:49:25.996606+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:49:31.653119+00:00'
diff --git a/data/nde/enriched/entries/1772_platform_rotterdamse_volkstuinen.yaml b/data/nde/enriched/entries/1772_platform_rotterdamse_volkstuinen.yaml
index c0d30d399a..92367f3c8f 100644
--- a/data/nde/enriched/entries/1772_platform_rotterdamse_volkstuinen.yaml
+++ b/data/nde/enriched/entries/1772_platform_rotterdamse_volkstuinen.yaml
@@ -129,3 +129,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:11.031227+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: https://rotterdamsevolkstuinen.nl/
+ directory: web/1772/rotterdamsevolkstuinen.nl
+ archive_timestamp: '2025-12-05T14:49:32.667850+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:49:37.740480+00:00'
diff --git a/data/nde/enriched/entries/1777_schitterend.yaml b/data/nde/enriched/entries/1777_schitterend.yaml
index 4e77858297..df9d03849b 100644
--- a/data/nde/enriched/entries/1777_schitterend.yaml
+++ b/data/nde/enriched/entries/1777_schitterend.yaml
@@ -124,3 +124,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:27.963852+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.schitterend.eu
+ directory: web/1777/schitterend.eu
+ archive_timestamp: '2025-12-05T14:49:41.665843+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:49:44.311813+00:00'
diff --git a/data/nde/enriched/entries/1781_shantynederland.yaml b/data/nde/enriched/entries/1781_shantynederland.yaml
index 1766a1aafa..f870592c57 100644
--- a/data/nde/enriched/entries/1781_shantynederland.yaml
+++ b/data/nde/enriched/entries/1781_shantynederland.yaml
@@ -123,3 +123,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:43.252473+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.shantynederland.nl
+ directory: web/1781/shantynederland.nl
+ archive_timestamp: '2025-12-05T14:50:16.025703+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:50:18.805153+00:00'
diff --git a/data/nde/enriched/entries/1782_sint_piterfeest_in_grou.yaml b/data/nde/enriched/entries/1782_sint_piterfeest_in_grou.yaml
index 6fc6008833..e728c921bb 100644
--- a/data/nde/enriched/entries/1782_sint_piterfeest_in_grou.yaml
+++ b/data/nde/enriched/entries/1782_sint_piterfeest_in_grou.yaml
@@ -138,3 +138,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:48.297646+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://sintpiter.nl/
+ directory: web/1782/sintpiter.nl
+ archive_timestamp: '2025-12-05T14:50:19.828255+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:50:24.887038+00:00'
diff --git a/data/nde/enriched/entries/1784_slow_food_presidium_limburgse_stroop.yaml b/data/nde/enriched/entries/1784_slow_food_presidium_limburgse_stroop.yaml
index b7e6c2f812..70edd4b52d 100644
--- a/data/nde/enriched/entries/1784_slow_food_presidium_limburgse_stroop.yaml
+++ b/data/nde/enriched/entries/1784_slow_food_presidium_limburgse_stroop.yaml
@@ -126,3 +126,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:40:47.331036+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.slowfood.nl
+ directory: web/1784/slowfood.nl
+ archive_timestamp: '2025-12-05T14:50:56.025853+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:51:04.028699+00:00'
diff --git a/data/nde/enriched/entries/1785_smederij_cornelis_pronk.yaml b/data/nde/enriched/entries/1785_smederij_cornelis_pronk.yaml
index d70d0055d1..d50255dec6 100644
--- a/data/nde/enriched/entries/1785_smederij_cornelis_pronk.yaml
+++ b/data/nde/enriched/entries/1785_smederij_cornelis_pronk.yaml
@@ -121,3 +121,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:13.619224+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.mondraopleidingen.nl
+ directory: web/1785/mondraopleidingen.nl
+ archive_timestamp: '2025-12-05T14:51:05.094452+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:51:09.298915+00:00'
diff --git a/data/nde/enriched/entries/1786_sociëteit_grolse_wanten.yaml b/data/nde/enriched/entries/1786_sociëteit_grolse_wanten.yaml
index 7be50c2b47..de546eef97 100644
--- a/data/nde/enriched/entries/1786_sociëteit_grolse_wanten.yaml
+++ b/data/nde/enriched/entries/1786_sociëteit_grolse_wanten.yaml
@@ -126,3 +126,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:09.549047+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.grolsewanten.nl
+ directory: web/1786/grolsewanten.nl
+ archive_timestamp: '2025-12-05T14:51:10.320780+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:51:12.558143+00:00'
diff --git a/data/nde/enriched/entries/1787_stichting_abrahamdag_oosterhout.yaml b/data/nde/enriched/entries/1787_stichting_abrahamdag_oosterhout.yaml
index 1820573372..c3854932d8 100644
--- a/data/nde/enriched/entries/1787_stichting_abrahamdag_oosterhout.yaml
+++ b/data/nde/enriched/entries/1787_stichting_abrahamdag_oosterhout.yaml
@@ -129,3 +129,10 @@ digital_platforms:
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:39:10.643862+00:00'
source_method: automated_extraction
+web_enrichment:
+ web_archives:
+ - url: http://www.abrahamdag.com
+ directory: web/1787/abrahamdag.com
+ archive_timestamp: '2025-12-05T14:51:13.580613+00:00'
+ status: new
+ platform_archive_timestamp: '2025-12-05T14:51:18.206782+00:00'
diff --git a/data/nde/enriched/entries/web/0000/kampwesterbork.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0000/kampwesterbork.nl/annotations_v1.7.0.yaml
index b2f9ac671f..cfba4d5dd8 100644
--- a/data/nde/enriched/entries/web/0000/kampwesterbork.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0000/kampwesterbork.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:28:56.925464+00:00'
+extraction_timestamp: '2025-12-05T14:33:32.893643+00:00'
source_url: https://kampwesterbork.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0000/kampwesterbork.nl/pages/index.html
session:
- session_id: llm-20251205142839
- started_at: '2025-12-05T14:28:39.028814+00:00'
- completed_at: '2025-12-05T14:28:56.922809+00:00'
+ session_id: llm-20251205143303
+ started_at: '2025-12-05T14:33:03.161405+00:00'
+ completed_at: '2025-12-05T14:33:32.891739+00:00'
agent:
name: unknown
version: 1.0.0
@@ -25,7 +25,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -37,22 +37,41 @@ session:
- claim_id: layout-2
claim_type: layout
claim_value: null
- text_content: Herinneringscentrum Kamp Westerbork
+ text_content: Plan je bezoek | Programma | Collectie | Educatie | Over ons |
+ Steun ons | Tickets
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[1]/div/div[1]/h1
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[2]/div/div[2]/div/nav
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/body/div[2]/div[1]/div/div[1]/h1
+ xpath: /html/body/div[2]/div/div[2]/div/nav
parent_claim_id: null
- claim_id: layout-3
+ claim_type: layout
+ claim_value: null
+ text_content: Herinneringscentrum Kamp Westerbork
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[4]/section/div/div/div[1]/div/h1
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/body/div[4]/section/div/div/div[1]/div/h1
+ parent_claim_id: null
+ - claim_id: layout-4
claim_type: layout
claim_value: null
text_content: In het Herinneringscentrum Kamp Westerbork vertellen we de verhalen
@@ -62,70 +81,15 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[1]/div/div[1]/p[1]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[4]/section/div/div/div[1]/div/p
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/body/div[2]/div[1]/div/div[1]/p[1]
- parent_claim_id: null
- - claim_id: layout-4
- claim_type: layout
- claim_value: null
- text_content: Plan je bezoek | Programma | Collectie | Educatie | Over ons |
- Steun ons | Tickets
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/div[2]/div/nav
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: /html/body/div[1]/div[1]/div/div[2]/div/nav
- parent_claim_id: null
- - claim_id: layout-5
- claim_type: layout
- claim_value: null
- text_content: Slideshow gallery with links.
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[2]/section/div/div/div[1]/ul
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: /html/body/div[1]/div[2]/section/div/div/div[1]/ul
- parent_claim_id: null
- - claim_id: layout-6
- claim_type: layout
- claim_value: null
- text_content: Footer with copyright and links.
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[11]/div/footer
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: /html/body/div[11]/div/footer
+ xpath: /html/body/div[4]/section/div/div/div[1]/div/p
parent_claim_id: null
entity:
- claim_id: entity-1
@@ -137,7 +101,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -155,43 +119,43 @@ session:
- claim_id: entity-2
claim_type: entity
claim_value: null
- text_content: Herinneringscentrum Kamp Westerbork
+ text_content: Waterbedrijf Groningen
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[1]/div/div[1]/h1
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[4]/section/div/div/div[2]/div/ul/li[1]/a/img/@alt
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
hypernym: GRP
- hyponym: GRP.HER
- class_uri: glam:HeritageCustodian
+ hyponym: GRP.COR
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-3
claim_type: entity
claim_value: null
- text_content: https://collecties.kampwesterbork.nl/
+ text_content: C&W de Boer Stichting
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/div[2]/section/div/div/div[2]/div/ul/li[2]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[6]/section/div/div/div/div/div/div/ul[2]/li[4]/div/div[2]/h4/a/@title
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
+ hypernym: GRP
+ hyponym: GRP.ASS
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -203,19 +167,19 @@ session:
- claim_id: entity-4
claim_type: entity
claim_value: null
- text_content: https://shop.kampwesterbork.nl/
+ text_content: Rabobank
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/div[2]/section/div/div/div[2]/div/ul/li[4]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[6]/section/div/div/div/div/div/div/ul[2]/li[4]/div/div[2]/h4/a/@title
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
+ hypernym: GRP
+ hyponym: GRP.COR
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -227,19 +191,19 @@ session:
- claim_id: entity-5
claim_type: entity
claim_value: null
- text_content: https://tickets.kampwesterbork.nl/nl/tickets
+ text_content: Landelijk Steunpunt Gastsprekers WOII-Heden
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/div[2]/div/nav/ul/li[7]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[10]/section/div/div/div/div/ul/li[2]/div/img/@alt
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
+ hypernym: GRP
+ hyponym: GRP.ASS
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -249,6 +213,126 @@ session:
recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-6
+ claim_type: entity
+ claim_value: null
+ text_content: Internetbureau Praes
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/footer/div/div/div/div[1]/div/a/@title
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: GRP
+ hyponym: GRP.COR
+ class_uri: org:FormalOrganization
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-7
+ claim_type: entity
+ claim_value: null
+ text_content: Geuchien Kreuze
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[6]/section/div/div/div/div/div/ul[1]/li[5]/div/img/@alt
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: AGT
+ hyponym: AGT.PER
+ class_uri: crm:E21_Person
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E21_Person
+ tei_element: null
+ recognition_confidence: 0.9
+ linking_confidence: 0.0
+ - claim_id: entity-8
+ claim_type: entity
+ claim_value: null
+ text_content: Namen Lezen
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[6]/section/div/div/div/div/div/ul[1]/li[5]/div/img/@alt
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.TIT
+ class_uri: crm:E35_Title
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E35_Title
+ tei_element: null
+ recognition_confidence: 0.8
+ linking_confidence: 0.0
+ - claim_id: entity-9
+ claim_type: entity
+ claim_value: null
+ text_content: kamp Westerbork
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[4]/section/div/div/div[1]/div/h1
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TOP
+ hyponym: TOP.LEG
+ class_uri: crm:E53_Place
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E53_Place
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-10
+ claim_type: entity
+ claim_value: null
+ text_content: nl-nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/@lang
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: THG
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E56_Language
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-11
claim_type: entity
claim_value: null
text_content: https://www.facebook.com/kampwesterbork/
@@ -256,8 +340,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[1]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[1]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -270,9 +354,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-7
+ - claim_id: entity-12
claim_type: entity
claim_value: null
text_content: https://www.instagram.com/kampwesterbork/
@@ -280,8 +364,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[2]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[2]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -294,9 +378,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-8
+ - claim_id: entity-13
claim_type: entity
claim_value: null
text_content: https://twitter.com/kampwesterbork
@@ -304,8 +388,32 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[3]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[3]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-14
+ claim_type: entity
+ claim_value: null
+ text_content: https://collecties.kampwesterbork.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[3]/section/div/div[2]/div/ul/li[2]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -320,127 +428,239 @@ session:
tei_element: null
recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-9
+ - claim_id: entity-15
claim_type: entity
claim_value: null
- text_content: Waterbedrijf Groningen
+ text_content: https://shop.kampwesterbork.nl/
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[2]/div/div[2]/div/div/ul/li[1]/h3/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[3]/section/div/div[2]/div/ul/li[4]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: GRP
- hyponym: GRP.COR
- class_uri: org:FormalOrganization
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.9
+ recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-10
+ - claim_id: entity-16
claim_type: entity
claim_value: null
- text_content: familieprogramma
+ text_content: https://tickets.kampwesterbork.nl/nl/tickets
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[2]/div/div[2]/div/div/ul/li[2]/h3/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[2]/div/div[2]/div/nav/ul/li[7]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-17
+ claim_type: entity
+ claim_value: null
+ text_content: Dutch
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[2]/div/div[1]/div/ul/li[1]/a/text()
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
hypernym: THG
- hyponym: THG.CON
- class_uri: crm:E28_Conceptual_Object
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E28_Conceptual_Object
+ cidoc_class: crm:E56_Language
tei_element: null
- recognition_confidence: 0.8
+ recognition_confidence: 0.9
linking_confidence: 0.0
- - claim_id: entity-11
+ - claim_id: entity-18
claim_type: entity
claim_value: null
- text_content: C&W de Boer Stichting
+ text_content: German
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div/div[2]/section/div/div[2]/div/div/div[4]/div/div[2]/div/h4/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[2]/div/div[1]/div/ul/li[2]/a/text()
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: GRP
- hyponym: GRP.COR
- class_uri: org:FormalOrganization
+ hypernym: THG
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: null
+ cidoc_class: crm:E56_Language
tei_element: null
recognition_confidence: 0.9
linking_confidence: 0.0
- - claim_id: entity-12
+ - claim_id: entity-19
claim_type: entity
claim_value: null
- text_content: Rabobank
+ text_content: English
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div/div[2]/section/div/div[2]/div/div/div[4]/div/div[2]/div/h4/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[2]/div/div[1]/div/ul/li[3]/a/text()
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: GRP
- hyponym: GRP.COR
- class_uri: org:FormalOrganization
+ hypernym: THG
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: null
+ cidoc_class: crm:E56_Language
tei_element: null
recognition_confidence: 0.9
linking_confidence: 0.0
- - claim_id: entity-13
- claim_type: entity
+ relationship:
+ - claim_id: rel-1
+ claim_type: relationship
claim_value: null
- text_content: Internetbureau Praes
+ text_content: ''
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[11]/div/footer/div/div[1]/div/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: ''
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.COR
- class_uri: org:FormalOrganization
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- relationship: []
+ confidence: 0.95
+ relationship_hypernym: REL.SPA
+ relationship_hyponym: REL.SPA.LOC
+ predicate_uris:
+ - crm:P53_has_former_or_current_location
+ - schema:location
+ - wdt:P276
+ extraction_confidence: 0.95
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-1
+ entity_type: GRP.HER
+ span_text: Herinneringscentrum Kamp Westerbork
+ uri: null
+ predicate:
+ uri: crm:P53_has_former_or_current_location
+ label: REL.SPA.LOC
+ direction: FORWARD
+ object:
+ entity_id: entity-9
+ entity_type: TOP.LEG
+ span_text: kamp Westerbork
+ uri: null
+ - claim_id: rel-2
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.8
+ relationship_hypernym: REL.ORG
+ relationship_hyponym: REL.ORG.FND
+ predicate_uris:
+ - schema:founder
+ - wdt:P112
+ extraction_confidence: 0.8
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-1
+ entity_type: GRP.HER
+ span_text: Herinneringscentrum Kamp Westerbork
+ uri: null
+ predicate:
+ uri: schema:founder
+ label: REL.ORG.FND
+ direction: FORWARD
+ object:
+ entity_id: entity-3
+ entity_type: GRP.ASS
+ span_text: C&W de Boer Stichting
+ uri: null
+ - claim_id: rel-3
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.8
+ relationship_hypernym: REL.ORG
+ relationship_hyponym: REL.ORG.FND
+ predicate_uris:
+ - schema:founder
+ - wdt:P112
+ extraction_confidence: 0.8
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-1
+ entity_type: GRP.HER
+ span_text: Herinneringscentrum Kamp Westerbork
+ uri: null
+ predicate:
+ uri: schema:founder
+ label: REL.ORG.FND
+ direction: FORWARD
+ object:
+ entity_id: entity-4
+ entity_type: GRP.COR
+ span_text: Rabobank
+ uri: null
aggregate:
- claim_id: claim-1
claim_type: aggregate
@@ -451,30 +671,13 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- claim_id: claim-2
- claim_type: aggregate
- claim_value: 'Herinneringscentrum Kamp Westerbork: meer dan een herinnering.
- Hier wordt het verhaal over het leven van slachtoffers en overlevenden verteld.'
- text_content: 'Herinneringscentrum Kamp Westerbork: meer dan een herinnering.
- Hier wordt het verhaal over het leven van slachtoffers en overlevenden verteld.'
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[3]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-3
claim_type: aggregate
claim_value: In het Herinneringscentrum Kamp Westerbork vertellen we de verhalen
van meer dan honderdduizend Joden en Sinti en Roma die vanuit Nederland naar
@@ -486,74 +689,14 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[2]/div[1]/div/div[1]/p[1]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[4]/section/div/div/div[1]/div/p
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-4
- claim_type: aggregate
- claim_value: nl/index.html
- text_content: nl/index.html
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/div[1]/div/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-5
- claim_type: aggregate
- claim_value: https://collecties.kampwesterbork.nl/
- text_content: https://collecties.kampwesterbork.nl/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[2]/section/div/div/div[2]/div/ul/li[2]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-6
- claim_type: aggregate
- claim_value: https://shop.kampwesterbork.nl/
- text_content: https://shop.kampwesterbork.nl/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[2]/section/div/div/div[2]/div/ul/li[4]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-7
- claim_type: aggregate
- claim_value: https://tickets.kampwesterbork.nl/nl/tickets
- text_content: https://tickets.kampwesterbork.nl/nl/tickets
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/div[2]/div/nav/ul/li[7]/a
- timestamp: '2025-12-05T14:28:56.921989+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-8
+ - claim_id: claim-3
claim_type: aggregate
claim_value: https://www.facebook.com/kampwesterbork/
text_content: https://www.facebook.com/kampwesterbork/
@@ -561,14 +704,14 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[1]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[1]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-9
+ - claim_id: claim-4
claim_type: aggregate
claim_value: https://www.instagram.com/kampwesterbork/
text_content: https://www.instagram.com/kampwesterbork/
@@ -576,14 +719,14 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[2]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[2]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-10
+ - claim_id: claim-5
claim_type: aggregate
claim_value: https://twitter.com/kampwesterbork
text_content: https://twitter.com/kampwesterbork
@@ -591,8 +734,53 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[10]/div[1]/section/div/div[1]/div/div/div[1]/a[3]
- timestamp: '2025-12-05T14:28:56.921989+00:00'
+ path: /html/body/div[11]/section/div/div/div[1]/div/div[1]/a[3]/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-6
+ claim_type: aggregate
+ claim_value: https://collecties.kampwesterbork.nl/
+ text_content: https://collecties.kampwesterbork.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[3]/section/div/div[2]/div/ul/li[2]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-7
+ claim_type: aggregate
+ claim_value: https://shop.kampwesterbork.nl/
+ text_content: https://shop.kampwesterbork.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[3]/section/div/div[2]/div/ul/li[4]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-8
+ claim_type: aggregate
+ claim_value: https://tickets.kampwesterbork.nl/nl/tickets
+ text_content: https://tickets.kampwesterbork.nl/nl/tickets
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[2]/div/div[2]/div/nav/ul/li[7]/a/@href
+ timestamp: '2025-12-05T14:33:32.890155+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -601,8 +789,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 13
- claim_count: 10
- relationship_count: 0
- layout_count: 6
+ entity_count: 19
+ claim_count: 8
+ relationship_count: 3
+ layout_count: 4
errors: *id001
diff --git a/data/nde/enriched/entries/web/0003/drentsmuseum.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0003/drentsmuseum.nl/annotations_v1.7.0.yaml
index 37fda9f56e..e0773bd1ca 100644
--- a/data/nde/enriched/entries/web/0003/drentsmuseum.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0003/drentsmuseum.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:29:09.620327+00:00'
+extraction_timestamp: '2025-12-05T14:33:47.525513+00:00'
source_url: https://drentsmuseum.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0003/drentsmuseum.nl/pages/index.html
session:
- session_id: llm-20251205142857
- started_at: '2025-12-05T14:28:57.614175+00:00'
- completed_at: '2025-12-05T14:29:09.619215+00:00'
+ session_id: llm-20251205143333
+ started_at: '2025-12-05T14:33:33.566746+00:00'
+ completed_at: '2025-12-05T14:33:47.524554+00:00'
agent:
name: unknown
version: 1.0.0
@@ -25,7 +25,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -35,6 +35,24 @@ session:
xpath: /html/head/title
parent_claim_id: null
- claim_id: layout-2
+ claim_type: layout
+ claim_value: null
+ text_content: Plan je bezoek Zien en doen Ontdek de collectie...
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[1]/nav
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/body/div[1]/nav
+ parent_claim_id: null
+ - claim_id: layout-3
claim_type: layout
claim_value: null
text_content: Drents Museum
@@ -42,34 +60,15 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/main/h1
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/main/h1
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/body/div[1]/main/h1
- parent_claim_id: null
- - claim_id: layout-3
- claim_type: layout
- claim_value: null
- text_content: Plan je bezoek Zien en doen Ontdek de collectie Over het museum
- ...
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/nav
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: /html/body/div[1]/div[1]/div/nav
+ xpath: /html/main/h1
parent_claim_id: null
entity:
- claim_id: entity-1
@@ -81,7 +80,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -99,19 +98,19 @@ session:
- claim_id: entity-2
claim_type: entity
claim_value: null
- text_content: Drents Museum
+ text_content: Assen
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[7]/@content
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/head/title
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: GRP
- hyponym: GRP.HER
- class_uri: glam:HeritageCustodian
+ hypernym: TOP
+ hyponym: TOP.SET
+ class_uri: schema:City
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -123,19 +122,19 @@ session:
- claim_id: entity-3
claim_type: entity
claim_value: null
- text_content: Assen
+ text_content: https://drentsmuseum.nl
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/head/script[1]
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -147,19 +146,67 @@ session:
- claim_id: entity-4
claim_type: entity
claim_value: null
- text_content: Assen
+ text_content: nl
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/main/section/article/div/div/div[1]/h3
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/html/@lang
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
+ hypernym: THG
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E56_Language
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-5
+ claim_type: entity
+ claim_value: null
+ text_content: Drents Museum in Assen
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/title
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.TTL
+ class_uri: crm:E35_Title
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E35_Title
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-6
+ claim_type: entity
+ claim_value: null
+ text_content: https://drentsmuseum.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[11]/@content
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -168,64 +215,16 @@ session:
tei_element: null
recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-5
- claim_type: entity
- claim_value: null
- text_content: DM De Buitenplaats
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/nav/div/div/ul/li[4]/ul/li[3]/a/span
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.HER
- class_uri: glam:HeritageCustodian
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-6
- claim_type: entity
- claim_value: null
- text_content: Eelde
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/nav/div/div/ul/li[4]/ul/li[3]/a/span
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- claim_id: entity-7
claim_type: entity
claim_value: null
- text_content: https://drentsmuseum.nl/
+ text_content: https://drentsmuseum.nl/index.html
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[12]/@content
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/head/link[20]/@href
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -243,98 +242,122 @@ session:
- claim_id: entity-8
claim_type: entity
claim_value: null
- text_content: nl
+ text_content: DM De Buitenplaats
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/@lang
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[4]/ul[1]/li[3]/a/span
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: GRP
+ hyponym: GRP.HER
+ class_uri: glam:HeritageCustodian
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-9
claim_type: entity
claim_value: null
- text_content: nl
+ text_content: Eelde
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[4]/ul[1]/li[3]/a/span
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: TOP
+ hyponym: TOP.SET
+ class_uri: schema:City
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: null
tei_element: null
recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-10
claim_type: entity
claim_value: null
- text_content: Nederlands
+ text_content: Drents Heideschaap van Carolein Smit
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/div[2]/div/div/ul/li[1]/a
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[3]/template/picture/img/@alt
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hyponym: THG.ART
+ class_uri: crm:E22_Human-Made_Object
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: crm:E22_Human-Made_Object
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 0.9
linking_confidence: 0.0
- claim_id: entity-11
claim_type: entity
claim_value: null
- text_content: English
+ text_content: Carolein Smit
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[1]/div[2]/div/div/ul/li[2]/a
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[3]/template/picture/img/@alt
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: AGT
+ hyponym: AGT.PER
+ class_uri: crm:E21_Person
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: crm:E21_Person
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 0.9
+ linking_confidence: 0.0
+ - claim_id: entity-12
+ claim_type: entity
+ claim_value: null
+ text_content: Collectie Drents Museum
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[3]/template/picture/img/@alt
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.COL
+ class_uri: crm:E35_Title
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E35_Title
+ tei_element: null
+ recognition_confidence: 0.9
linking_confidence: 0.0
relationship:
- claim_id: rel-1
@@ -346,7 +369,7 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -362,7 +385,7 @@ session:
source_claim: false
attributed_to: null
subject:
- entity_id: entity-2
+ entity_id: entity-1
entity_type: GRP.HER
span_text: Drents Museum
uri: null
@@ -371,7 +394,7 @@ session:
label: REL.SPA.LOC
direction: FORWARD
object:
- entity_id: entity-4
+ entity_id: entity-2
entity_type: TOP.SET
span_text: Assen
uri: null
@@ -384,33 +407,34 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.8
- relationship_hypernym: REL.ORG
- relationship_hyponym: REL.ORG.SUB
+ confidence: 0.9
+ relationship_hypernym: REL.SPA
+ relationship_hyponym: REL.SPA.LOC
predicate_uris:
- - schema:subOrganization
- - wdt:P355
- extraction_confidence: 0.8
+ - crm:P53_has_former_or_current_location
+ - schema:location
+ - wdt:P276
+ extraction_confidence: 0.9
negation: false
hypothetical: false
source_claim: false
attributed_to: null
subject:
- entity_id: entity-5
+ entity_id: entity-8
entity_type: GRP.HER
span_text: DM De Buitenplaats
uri: null
predicate:
- uri: schema:subOrganization
- label: REL.ORG.SUB
+ uri: crm:P53_has_former_or_current_location
+ label: REL.SPA.LOC
direction: FORWARD
object:
- entity_id: entity-2
- entity_type: GRP.HER
- span_text: Drents Museum
+ entity_id: entity-9
+ entity_type: TOP.SET
+ span_text: Eelde
uri: null
- claim_id: rel-3
claim_type: relationship
@@ -421,34 +445,108 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.85
+ relationship_hypernym: REL.ORG
+ relationship_hyponym: REL.ORG.SUB
+ predicate_uris:
+ - schema:subOrganization
+ - wdt:P355
+ extraction_confidence: 0.85
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-8
+ entity_type: GRP.HER
+ span_text: DM De Buitenplaats
+ uri: null
+ predicate:
+ uri: schema:subOrganization
+ label: REL.ORG.SUB
+ direction: FORWARD
+ object:
+ entity_id: entity-1
+ entity_type: GRP.HER
+ span_text: Drents Museum
+ uri: null
+ - claim_id: rel-4
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 0.8
- relationship_hypernym: REL.SPA
- relationship_hyponym: REL.SPA.LOC
+ relationship_hypernym: REL.CRE
+ relationship_hyponym: REL.CRE.ART
predicate_uris:
- - crm:P53_has_former_or_current_location
- - schema:location
- - wdt:P276
+ - crm:P14_carried_out_by
+ - wdt:P170
extraction_confidence: 0.8
negation: false
hypothetical: false
source_claim: false
attributed_to: null
subject:
- entity_id: entity-5
- entity_type: GRP.HER
- span_text: DM De Buitenplaats
+ entity_id: entity-11
+ entity_type: AGT.PER
+ span_text: Carolein Smit
uri: null
predicate:
- uri: crm:P53_has_former_or_current_location
- label: REL.SPA.LOC
+ uri: crm:P14_carried_out_by
+ label: REL.CRE.ART
direction: FORWARD
object:
- entity_id: entity-6
- entity_type: TOP.SET
- span_text: Eelde
+ entity_id: null
+ entity_type: THG.ART
+ span_text: Drents Heideschaap
+ uri: null
+ - claim_id: rel-5
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.8
+ relationship_hypernym: REL.CUS
+ relationship_hyponym: REL.CUS.KEP
+ predicate_uris:
+ - crm:P50_has_current_keeper
+ - rico:hasOrHadHolder
+ - wdt:P195
+ extraction_confidence: 0.8
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: null
+ entity_type: THG.ART
+ span_text: Drents Heideschaap
+ uri: null
+ predicate:
+ uri: crm:P50_has_current_keeper
+ label: REL.CUS.KEP
+ direction: FORWARD
+ object:
+ entity_id: entity-1
+ entity_type: GRP.HER
+ span_text: Drents Museum
uri: null
aggregate:
- claim_id: claim-1
@@ -459,14 +557,44 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/main/h1
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- claim_id: claim-2
+ claim_type: aggregate
+ claim_value: DM De Buitenplaats
+ text_content: DM De Buitenplaats
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[1]/nav/div[2]/div[1]/ul[1]/li[4]/ul[1]/li[3]/a/span
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-3
+ claim_type: aggregate
+ claim_value: https://drentsmuseum.nl
+ text_content: https://drentsmuseum.nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[1]
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-4
claim_type: aggregate
claim_value: Internationale tentoonstellingen en een rijke collectie archeologie,
kunst rond 1900, Drentse geschiedenis, Schilders van Drenthe en hedendaags
@@ -478,53 +606,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[8]/@content
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-3
- claim_type: aggregate
- claim_value: https://drentsmuseum.nl/
- text_content: https://drentsmuseum.nl/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[12]/@content
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-4
- claim_type: aggregate
- claim_value: Assen
- text_content: Assen
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:09.618602+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-5
- claim_type: aggregate
- claim_value: DM De Buitenplaats, Eelde
- text_content: DM De Buitenplaats, Eelde
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[1]/div[1]/div/nav/div/div/ul/li[4]/ul/li[3]/a/span
- timestamp: '2025-12-05T14:29:09.618602+00:00'
+ path: /html/head/meta[9]/@content
+ timestamp: '2025-12-05T14:33:47.524048+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -533,8 +616,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 11
- claim_count: 5
- relationship_count: 3
+ entity_count: 12
+ claim_count: 4
+ relationship_count: 5
layout_count: 3
errors: *id001
diff --git a/data/nde/enriched/entries/web/0004/dmdebuitenplaats.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0004/dmdebuitenplaats.nl/annotations_v1.7.0.yaml
index c737aba274..871f6d60d8 100644
--- a/data/nde/enriched/entries/web/0004/dmdebuitenplaats.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0004/dmdebuitenplaats.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:29:19.756870+00:00'
+extraction_timestamp: '2025-12-05T14:34:00.248882+00:00'
source_url: https://dmdebuitenplaats.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0004/dmdebuitenplaats.nl/pages/index.html
session:
- session_id: llm-20251205142910
- started_at: '2025-12-05T14:29:10.276083+00:00'
- completed_at: '2025-12-05T14:29:19.756516+00:00'
+ session_id: llm-20251205143348
+ started_at: '2025-12-05T14:33:48.183275+00:00'
+ completed_at: '2025-12-05T14:34:00.248438+00:00'
agent:
name: unknown
version: 1.0.0
@@ -15,9 +15,153 @@ session:
file: null
hash: null
claims:
- layout: []
+ layout:
+ - claim_id: layout-1
+ claim_type: layout
+ claim_value: null
+ text_content: Buitenplaats - Drents Museum De Buitenplaats in Eelde
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/head/title
+ parent_claim_id: null
+ - claim_id: layout-2
+ claim_type: layout
+ claim_value: null
+ text_content: Plan je bezoek, Zien en doen, Over De Buitenplaats
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //ul[contains(@class, 'm-nav__primary')]
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: //ul[contains(@class, 'm-nav__primary')]
+ parent_claim_id: null
+ - claim_id: layout-3
+ claim_type: layout
+ claim_value: null
+ text_content: Het museum voor art nouveau en kunst rond 1900.
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[@name='description']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/head/meta[@name='description']
+ parent_claim_id: null
+ - claim_id: layout-4
+ claim_type: layout
+ claim_value: null
+ text_content: De Buitenplaats
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //a[contains(@class, 'm-header__logo')]
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: //a[contains(@class, 'm-header__logo')]
+ parent_claim_id: null
entity:
- claim_id: entity-1
+ claim_type: entity
+ claim_value: null
+ text_content: https://dmdebuitenplaats.nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[1]
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-2
+ claim_type: entity
+ claim_value: null
+ text_content: https://drentsmuseum.nl/collectie/overzicht?referer=debuitenplaats
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body//a[contains(@href, 'drentsmuseum.nl')]
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-3
+ claim_type: entity
+ claim_value: null
+ text_content: Drents Museum De Buitenplaats in Eelde
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.TIT
+ class_uri: crm:E35_Title
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E35_Title
+ tei_element: null
+ recognition_confidence: 1.0
+ linking_confidence: 0.0
+ - claim_id: entity-4
claim_type: entity
claim_value: null
text_content: Drents Museum De Buitenplaats
@@ -26,7 +170,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -39,33 +183,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-2
- claim_type: entity
- claim_value: null
- text_content: Drents Museum De Buitenplaats
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@property='og:title']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.HER
- class_uri: glam:HeritageCustodian
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
- - claim_id: entity-3
+ - claim_id: entity-5
claim_type: entity
claim_value: null
text_content: Eelde
@@ -74,7 +194,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -87,103 +207,175 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-4
- claim_type: entity
- claim_value: null
- text_content: https://dmdebuitenplaats.nl/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 1.0
- linking_confidence: 0.0
- - claim_id: entity-5
- claim_type: entity
- claim_value: null
- text_content: https://dmdebuitenplaats.nl/media/1/De-Buitenplaats/Museumgebouw/_1200x630_crop_center-center_82_none/ns/se20200805-buitenplaats-10.jpg?v=1763993107%2C0.4382%2C0.4184
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@property='og:image']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-6
claim_type: entity
claim_value: null
- text_content: nl
+ text_content: Buitenplaats
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html[@lang='nl']/@lang
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ path: /html/head/meta[@property='og:site_name']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: APP
+ hyponym: APP.TIT
+ class_uri: crm:E35_Title
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: crm:E35_Title
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-7
claim_type: entity
claim_value: null
- text_content: en
+ text_content: Drents
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@property='og:locale:alternate']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: TOP
+ hyponym: TOP.REG
+ class_uri: schema:AdministrativeArea
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.85
+ linking_confidence: 0.0
+ - claim_id: entity-8
+ claim_type: entity
+ claim_value: null
+ text_content: art nouveau
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[@name='description']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: THG
+ hyponym: THG.CON
+ class_uri: crm:E28_Conceptual_Object
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E28_Conceptual_Object
+ tei_element: null
+ recognition_confidence: 0.9
+ linking_confidence: 0.0
+ - claim_id: entity-9
+ claim_type: entity
+ claim_value: null
+ text_content: The Mucha Experience
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //span[text()='The Mucha Experience']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.EXH
+ class_uri: crm:E35_Title
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E35_Title
+ tei_element: null
+ recognition_confidence: 0.9
+ linking_confidence: 0.0
+ - claim_id: entity-10
+ claim_type: entity
+ claim_value: null
+ text_content: Mucha
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //span[text()='The Mucha Experience']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: AGT
+ hyponym: AGT.PER
+ class_uri: crm:E21_Person
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E21_Person
+ tei_element: null
+ recognition_confidence: 0.8
+ linking_confidence: 0.0
+ - claim_id: entity-11
+ claim_type: entity
+ claim_value: null
+ text_content: Nijsinghhuis
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //span[text()='Nijsinghhuis']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TOP
+ hyponym: TOP.BLD
+ class_uri: crm:E18_Physical_Thing
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E18_Physical_Thing
+ tei_element: null
+ recognition_confidence: 0.8
+ linking_confidence: 0.0
+ - claim_id: entity-12
+ claim_type: entity
+ claim_value: null
+ text_content: Museumtuin
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //span[text()='Museumtuin']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TOP
+ hyponym: TOP.BLD
+ class_uri: crm:E18_Physical_Thing
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: crm:E18_Physical_Thing
+ tei_element: null
+ recognition_confidence: 0.8
linking_confidence: 0.0
relationship:
- claim_id: rel-1
@@ -195,7 +387,7 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 0.9
@@ -211,7 +403,7 @@ session:
source_claim: false
attributed_to: null
subject:
- entity_id: entity-2
+ entity_id: entity-4
entity_type: GRP.HER
span_text: Drents Museum De Buitenplaats
uri: null
@@ -220,21 +412,58 @@ session:
label: REL.SPA.LOC
direction: FORWARD
object:
- entity_id: entity-3
+ entity_id: entity-5
entity_type: TOP.SET
span_text: Eelde
uri: null
+ - claim_id: rel-2
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.85
+ relationship_hypernym: REL.CUS
+ relationship_hyponym: REL.CUS.COL
+ predicate_uris:
+ - edm:isShownAt
+ - wdt:P195
+ extraction_confidence: 0.85
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-8
+ entity_type: THG.CON
+ span_text: art nouveau
+ uri: null
+ predicate:
+ uri: edm:isShownAt
+ label: REL.CUS.COL
+ direction: FORWARD
+ object:
+ entity_id: entity-4
+ entity_type: GRP.HER
+ span_text: Drents Museum De Buitenplaats
+ uri: null
aggregate:
- claim_id: claim-1
claim_type: aggregate
- claim_value: Drents Museum De Buitenplaats in Eelde
- text_content: Drents Museum De Buitenplaats in Eelde
+ claim_value: Drents Museum De Buitenplaats
+ text_content: Drents Museum De Buitenplaats
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -242,14 +471,14 @@ session:
relationship_claims: []
- claim_id: claim-2
claim_type: aggregate
- claim_value: Het museum voor art nouveau en kunst rond 1900.
- text_content: Het museum voor art nouveau en kunst rond 1900.
+ claim_value: Buitenplaats
+ text_content: Buitenplaats
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ path: /html/head/meta[@property='og:site_name']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -257,14 +486,59 @@ session:
relationship_claims: []
- claim_id: claim-3
claim_type: aggregate
- claim_value: https://dmdebuitenplaats.nl/
- text_content: https://dmdebuitenplaats.nl/
+ claim_value: Eelde
+ text_content: Eelde
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T14:29:19.755722+00:00'
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-4
+ claim_type: aggregate
+ claim_value: Het museum voor art nouveau en kunst rond 1900.
+ text_content: Het museum voor art nouveau en kunst rond 1900.
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[@name='description']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-5
+ claim_type: aggregate
+ claim_value: https://dmdebuitenplaats.nl
+ text_content: https://dmdebuitenplaats.nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[1]
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-6
+ claim_type: aggregate
+ claim_value: The Mucha Experience
+ text_content: The Mucha Experience
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //span[text()='The Mucha Experience']
+ timestamp: '2025-12-05T14:34:00.248109+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -273,8 +547,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 7
- claim_count: 3
- relationship_count: 1
- layout_count: 0
+ entity_count: 12
+ claim_count: 6
+ relationship_count: 2
+ layout_count: 4
errors: *id001
diff --git a/data/nde/enriched/entries/web/0005/aaenhunze.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0005/aaenhunze.nl/annotations_v1.7.0.yaml
index d1a77fa56b..8ab8427cf7 100644
--- a/data/nde/enriched/entries/web/0005/aaenhunze.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0005/aaenhunze.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:29:30.296396+00:00'
+extraction_timestamp: '2025-12-05T14:34:15.077257+00:00'
source_url: https://www.aaenhunze.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0005/aaenhunze.nl/pages/index.html
session:
- session_id: llm-20251205142920
- started_at: '2025-12-05T14:29:20.401788+00:00'
- completed_at: '2025-12-05T14:29:30.295157+00:00'
+ session_id: llm-20251205143400
+ started_at: '2025-12-05T14:34:00.895522+00:00'
+ completed_at: '2025-12-05T14:34:15.074468+00:00'
agent:
name: unknown
version: 1.0.0
@@ -15,7 +15,61 @@ session:
file: null
hash: null
claims:
- layout: []
+ layout:
+ - claim_id: layout-1
+ claim_type: layout
+ claim_value: null
+ text_content: Home - Gemeente Aa en Hunze
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/head/title
+ parent_claim_id: null
+ - claim_id: layout-2
+ claim_type: layout
+ claim_value: null
+ text_content: '{"geo":{"@type":"GeoCoordinates"...'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/head/script[8]
+ parent_claim_id: null
+ - claim_id: layout-3
+ claim_type: layout
+ claim_value: null
+ text_content: Alle onderwerpen Contact
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/body/div[2]/div[1]/div[1]/div[1]/div[1]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/body/div[2]/div[1]/div[1]/div[1]/div[1]
+ parent_claim_id: null
entity:
- claim_id: entity-1
claim_type: entity
@@ -25,8 +79,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -44,26 +98,26 @@ session:
- claim_id: entity-2
claim_type: entity
claim_value: null
- text_content: Spiekersteeg 1
+ text_content: CityHall
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: TOP
- hyponym: TOP.ADR
- class_uri: schema:PostalAddress
+ hypernym: THG
+ hyponym: THG.CON
+ class_uri: crm:E28_Conceptual_Object
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: null
+ cidoc_class: crm:E28_Conceptual_Object
tei_element: null
- recognition_confidence: 0.9
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-3
claim_type: entity
@@ -73,8 +127,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -87,9 +141,33 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.9
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-4
+ claim_type: entity
+ claim_value: null
+ text_content: Spiekersteeg 1
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TOP
+ hyponym: TOP.ADR
+ class_uri: schema:PostalAddress
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-5
claim_type: entity
claim_value: null
text_content: https://www.aaenhunze.nl/Home
@@ -97,8 +175,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[2]/@content
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/meta[2]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -113,16 +191,16 @@ session:
tei_element: null
recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-5
+ - claim_id: entity-6
claim_type: entity
claim_value: null
- text_content: Monday 09:00-16:00
+ text_content: 'Monday: 09:00-16:00'
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -135,31 +213,127 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.9
+ recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-6
+ - claim_id: entity-7
claim_type: entity
claim_value: null
- text_content: Archief gemeente Aa en Hunze
+ text_content: 'Tuesday: 09:00-16:00'
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[1]/div[1]/div[1]/div[1]/nav[1]/ul[1]/li[2]/ul[1]/li[7]/a
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.COL
- class_uri: crm:E35_Title
+ hypernym: TMP
+ hyponym: TMP.OPH
+ class_uri: schema:OpeningHoursSpecification
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E35_Title
+ cidoc_class: null
tei_element: null
- recognition_confidence: 0.8
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-8
+ claim_type: entity
+ claim_value: null
+ text_content: 'Wednesday: 09:00-16:00'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TMP
+ hyponym: TMP.OPH
+ class_uri: schema:OpeningHoursSpecification
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-9
+ claim_type: entity
+ claim_value: null
+ text_content: 'Thursday: 09:00-19:00'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TMP
+ hyponym: TMP.OPH
+ class_uri: schema:OpeningHoursSpecification
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-10
+ claim_type: entity
+ claim_value: null
+ text_content: 'Friday: 09:00-16:00'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TMP
+ hyponym: TMP.OPH
+ class_uri: schema:OpeningHoursSpecification
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-11
+ claim_type: entity
+ claim_value: null
+ text_content: tel:0592 267777
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
linking_confidence: 0.0
relationship:
- claim_id: rel-1
@@ -171,17 +345,17 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.9
+ confidence: 0.95
relationship_hypernym: REL.SPA
relationship_hyponym: REL.SPA.LOC
predicate_uris:
- crm:P53_has_former_or_current_location
- schema:location
- wdt:P276
- extraction_confidence: 0.9
+ extraction_confidence: 0.95
negation: false
hypothetical: false
source_claim: false
@@ -196,7 +370,7 @@ session:
label: REL.SPA.LOC
direction: FORWARD
object:
- entity_id: entity-2
+ entity_id: entity-4
entity_type: TOP.ADR
span_text: Spiekersteeg 1
uri: null
@@ -209,17 +383,17 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.9
+ confidence: 0.95
relationship_hypernym: REL.SPA
relationship_hyponym: REL.SPA.LOC
predicate_uris:
- crm:P53_has_former_or_current_location
- schema:location
- wdt:P276
- extraction_confidence: 0.9
+ extraction_confidence: 0.95
negation: false
hypothetical: false
source_claim: false
@@ -238,6 +412,43 @@ session:
entity_type: GEO.PNT
span_text: 53.0050357540, 6.7600035667
uri: null
+ - claim_id: rel-3
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.9
+ relationship_hypernym: REL.ORG
+ relationship_hyponym: REL.ORG.SUB
+ predicate_uris:
+ - schema:subOrganization
+ - wdt:P355
+ extraction_confidence: 0.9
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-2
+ entity_type: THG.CON
+ span_text: CityHall
+ uri: null
+ predicate:
+ uri: schema:subOrganization
+ label: REL.ORG.SUB
+ direction: FORWARD
+ object:
+ entity_id: entity-1
+ entity_type: GRP.GOV
+ span_text: Gemeente Aa en Hunze
+ uri: null
aggregate:
- claim_id: claim-1
claim_type: aggregate
@@ -247,8 +458,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -262,14 +473,29 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- claim_id: claim-3
+ claim_type: aggregate
+ claim_value: Monday - Friday 09:00-16:00, Thursday 09:00-19:00
+ text_content: Monday - Friday 09:00-16:00, Thursday 09:00-19:00
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.8
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-4
claim_type: aggregate
claim_value: 0592 267777
text_content: 0592 267777
@@ -277,30 +503,13 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/script[8]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-4
- claim_type: aggregate
- claim_value: 'Monday: 09:00-16:00, Tuesday: 09:00-16:00, Wednesday: 09:00-16:00,
- Thursday: 09:00-19:00, Friday: 09:00-16:00'
- text_content: 'Monday: 09:00-16:00, Tuesday: 09:00-16:00, Wednesday: 09:00-16:00,
- Thursday: 09:00-19:00, Friday: 09:00-16:00'
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.5
- entity_claims: []
- relationship_claims: []
- claim_id: claim-5
claim_type: aggregate
claim_value: https://www.aaenhunze.nl/Home
@@ -309,33 +518,20 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[2]/@content
- timestamp: '2025-12-05T14:29:30.294910+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-6
- claim_type: aggregate
- claim_value: Municipality of Aa en Hunze
- text_content: Municipality of Aa en Hunze
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/script[1]/text()
- timestamp: '2025-12-05T14:29:30.294910+00:00'
+ path: /html/head/meta[2]
+ timestamp: '2025-12-05T14:34:15.072703+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
config: {}
- errors: &id001 []
+ errors: &id001
+ - '[VALIDATION WARNING] rel-3: Relationship ''REL.ORG.SUB'' has invalid domain:
+ subject type ''THG.CON'' not in allowed types [''GRP'', ''APP.WEB'', ''TOP.BLD'']'
summary:
- entity_count: 6
- claim_count: 6
- relationship_count: 2
- layout_count: 0
+ entity_count: 11
+ claim_count: 5
+ relationship_count: 3
+ layout_count: 3
errors: *id001
diff --git a/data/nde/enriched/entries/web/0006/borger-odoorn.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0006/borger-odoorn.nl/annotations_v1.7.0.yaml
index b3f8a29b50..1a63d7cdef 100644
--- a/data/nde/enriched/entries/web/0006/borger-odoorn.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0006/borger-odoorn.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:29:39.609021+00:00'
+extraction_timestamp: '2025-12-05T14:34:22.648349+00:00'
source_url: https://www.borger-odoorn.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0006/borger-odoorn.nl/pages/index.html
session:
- session_id: llm-20251205142930
- started_at: '2025-12-05T14:29:30.966285+00:00'
- completed_at: '2025-12-05T14:29:39.608736+00:00'
+ session_id: llm-20251205143415
+ started_at: '2025-12-05T14:34:15.777962+00:00'
+ completed_at: '2025-12-05T14:34:22.647466+00:00'
agent:
name: unknown
version: 1.0.0
@@ -24,15 +24,15 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/head
+ xpath: /html/head/title
parent_claim_id: null
entity:
- claim_id: entity-1
@@ -44,7 +44,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -57,33 +57,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.99
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-2
- claim_type: entity
- claim_value: null
- text_content: Borger-Odoorn
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:39.608658+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-3
claim_type: entity
claim_value: null
text_content: https://www.borger-odoorn.nl/
@@ -91,8 +67,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[4]/@content
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ path: /html/head/meta[7]/@content
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -107,69 +83,31 @@ session:
tei_element: null
recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-4
+ - claim_id: entity-3
claim_type: entity
claim_value: null
- text_content: nl
+ text_content: https://www.borger-odoorn.nl/images/logoe6d4ba621b3c914d.svg
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/@lang
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ path: /html/head/meta[8]/@content
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: THG
- hyponym: THG.LNG
- class_uri: crm:E56_Language
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E56_Language
+ cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 0.9
linking_confidence: 0.0
- relationship:
- - claim_id: rel-1
- claim_type: relationship
- claim_value: null
- text_content: ''
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: ''
- timestamp: '2025-12-05T14:29:39.608658+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.9
- relationship_hypernym: REL.SPA
- relationship_hyponym: REL.SPA.LOC
- predicate_uris:
- - crm:P53_has_former_or_current_location
- - schema:location
- - wdt:P276
- extraction_confidence: 0.9
- negation: false
- hypothetical: false
- source_claim: false
- attributed_to: null
- subject:
- entity_id: entity-1
- entity_type: GRP.GOV
- span_text: Gemeente Borger-Odoorn
- uri: null
- predicate:
- uri: crm:P53_has_former_or_current_location
- label: REL.SPA.LOC
- direction: FORWARD
- object:
- entity_id: entity-2
- entity_type: TOP.SET
- span_text: Borger-Odoorn
- uri: null
+ relationship: []
aggregate:
- claim_id: claim-1
claim_type: aggregate
@@ -180,13 +118,28 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- claim_id: claim-2
+ claim_type: aggregate
+ claim_value: https://www.borger-odoorn.nl/
+ text_content: https://www.borger-odoorn.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[7]/@content
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-3
claim_type: aggregate
claim_value: Officiële website van de gemeente Borger-Odoorn met informatie
over onze (digitale) diensten, de organisatie en het bestuur
@@ -196,23 +149,23 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[2]/@content
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ path: /html/head/meta[3]/@content
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-3
+ - claim_id: claim-4
claim_type: aggregate
- claim_value: https://www.borger-odoorn.nl/
- text_content: https://www.borger-odoorn.nl/
+ claim_value: nl
+ text_content: nl
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[4]/@content
- timestamp: '2025-12-05T14:29:39.608658+00:00'
+ path: /html/@lang
+ timestamp: '2025-12-05T14:34:22.647242+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -221,8 +174,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 4
- claim_count: 3
- relationship_count: 1
+ entity_count: 3
+ claim_count: 4
+ relationship_count: 0
layout_count: 1
errors: *id001
diff --git a/data/nde/enriched/entries/web/0007/coevorden.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0007/coevorden.nl/annotations_v1.7.0.yaml
index 17e17cb41c..4385d51e94 100644
--- a/data/nde/enriched/entries/web/0007/coevorden.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0007/coevorden.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:29:49.580990+00:00'
+extraction_timestamp: '2025-12-05T14:34:31.972539+00:00'
source_url: https://www.coevorden.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0007/coevorden.nl/pages/index.html
session:
- session_id: llm-20251205142940
- started_at: '2025-12-05T14:29:40.248076+00:00'
- completed_at: '2025-12-05T14:29:49.580606+00:00'
+ session_id: llm-20251205143423
+ started_at: '2025-12-05T14:34:23.309417+00:00'
+ completed_at: '2025-12-05T14:34:31.971290+00:00'
agent:
name: unknown
version: 1.0.0
@@ -19,51 +19,32 @@ session:
- claim_id: layout-1
claim_type: layout
claim_value: null
- text_content: Home | Gemeente Coevorden
+ text_content:
Home | Gemeente Coevorden
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/head/title
- parent_claim_id: null
- - claim_id: layout-2
- claim_type: layout
- claim_value: null
- text_content: Website van de gemeente Coevorden. Met digitale informatie, producten
- en diensten voor al onze inwoners en ondernemers.
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: /html/head/meta[@name='description']/@content
+ xpath: /html/head
parent_claim_id: null
entity:
- claim_id: entity-1
claim_type: entity
claim_value: null
- text_content: Gemeente Coevorden
+ text_content: gemeente Coevorden
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -76,7 +57,7 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-2
claim_type: entity
@@ -86,8 +67,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head/meta[12]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -100,57 +81,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-3
- claim_type: entity
- claim_value: null
- text_content: Gemeente Coevorden
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@property='og:site_name']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.GOV
- class_uri: schema:GovernmentOrganization
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 1.0
- linking_confidence: 0.0
- - claim_id: entity-4
- claim_type: entity
- claim_value: null
- text_content: https://www.coevorden.nl/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: APP
- hyponym: APP.URL
- class_uri: schema:URL
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 1.0
- linking_confidence: 0.0
- - claim_id: entity-5
claim_type: entity
claim_value: null
text_content: Coevorden
@@ -159,7 +92,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -174,7 +107,31 @@ session:
tei_element: null
recognition_confidence: 0.95
linking_confidence: 0.0
- - claim_id: entity-6
+ - claim_id: entity-4
+ claim_type: entity
+ claim_value: null
+ text_content: https://www.coevorden.nl/
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[5]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: APP
+ hyponym: APP.URL
+ class_uri: schema:URL
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.95
+ linking_confidence: 0.0
+ - claim_id: entity-5
claim_type: entity
claim_value: null
text_content: nl
@@ -182,8 +139,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html[@lang='nl']/@lang
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/@lang
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -196,49 +153,26 @@ session:
isil_id: null
cidoc_class: crm:E56_Language
tei_element: null
- recognition_confidence: 0.9
+ recognition_confidence: 1.0
linking_confidence: 0.0
- relationship:
- - claim_id: rel-1
- claim_type: relationship
- claim_value: null
- text_content: ''
+ relationship: []
+ aggregate:
+ - claim_id: claim-1
+ claim_type: aggregate
+ claim_value: gemeente Coevorden
+ text_content: gemeente Coevorden
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: ''
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.9
- relationship_hypernym: REL.SPA
- relationship_hyponym: REL.SPA.LOC
- predicate_uris:
- - crm:P53_has_former_or_current_location
- - schema:location
- - wdt:P276
- extraction_confidence: 0.9
- negation: false
- hypothetical: false
- source_claim: false
- attributed_to: null
- subject:
- entity_id: entity-3
- entity_type: GRP.GOV
- span_text: Gemeente Coevorden
- uri: null
- predicate:
- uri: crm:P53_has_former_or_current_location
- label: REL.SPA.LOC
- direction: FORWARD
- object:
- entity_id: entity-5
- entity_type: TOP.SET
- span_text: Coevorden
- uri: null
- aggregate:
- - claim_id: claim-1
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-2
claim_type: aggregate
claim_value: Gemeente Coevorden
text_content: Gemeente Coevorden
@@ -246,14 +180,14 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head/meta[12]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-2
+ - claim_id: claim-3
claim_type: aggregate
claim_value: Website van de gemeente Coevorden. Met digitale informatie, producten
en diensten voor al onze inwoners en ondernemers.
@@ -263,14 +197,14 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head/meta[3]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- - claim_id: claim-3
+ - claim_id: claim-4
claim_type: aggregate
claim_value: https://www.coevorden.nl/
text_content: https://www.coevorden.nl/
@@ -278,8 +212,68 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T14:29:49.580295+00:00'
+ path: /html/head/meta[5]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-5
+ claim_type: aggregate
+ claim_value: nl
+ text_content: nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/@lang
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-6
+ claim_type: aggregate
+ claim_value: '1280'
+ text_content: '1280'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[8]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-7
+ claim_type: aggregate
+ claim_value: '670'
+ text_content: '670'
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[9]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-8
+ claim_type: aggregate
+ claim_value: nl
+ text_content: nl
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[11]
+ timestamp: '2025-12-05T14:34:31.969448+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -288,8 +282,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 6
- claim_count: 3
- relationship_count: 1
- layout_count: 2
+ entity_count: 5
+ claim_count: 8
+ relationship_count: 0
+ layout_count: 1
errors: *id001
diff --git a/data/nde/enriched/entries/web/0008/dewolden.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0008/dewolden.nl/annotations_v1.7.0.yaml
index 02ea329bf9..65e8fe1f92 100644
--- a/data/nde/enriched/entries/web/0008/dewolden.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0008/dewolden.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T14:30:08.140350+00:00'
+extraction_timestamp: '2025-12-05T14:34:42.827644+00:00'
source_url: https://www.dewolden.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0008/dewolden.nl/pages/index.html
session:
- session_id: llm-20251205142950
- started_at: '2025-12-05T14:29:50.224341+00:00'
- completed_at: '2025-12-05T14:30:08.139202+00:00'
+ session_id: llm-20251205143432
+ started_at: '2025-12-05T14:34:32.716926+00:00'
+ completed_at: '2025-12-05T14:34:42.826496+00:00'
agent:
name: unknown
version: 1.0.0
@@ -25,7 +25,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -42,33 +42,34 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[2]/div/div
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: //div[@class='visitaddress']//div[@class='ce-bodytext']
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/body/div[4]/div[2]/div[3]/div[2]/div/div
+ xpath: //div[@class='visitaddress']//div[@class='ce-bodytext']
parent_claim_id: null
- claim_id: layout-3
claim_type: layout
claim_value: null
- text_content: Postadres Postbus 20 7920 AA Zuidwolde gemeente@dewolden.nl
+ text_content: De officiële website van gemeente De Wolden met informatie over
+ onze diensten en bestuur...
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[3]/div[2]/div
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: /html/head/meta[@name='description']/@content
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: /html/body/div[4]/div[2]/div[3]/div[3]/div[2]/div
+ xpath: /html/head/meta[@name='description']/@content
parent_claim_id: null
entity:
- claim_id: entity-1
@@ -80,7 +81,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -98,13 +99,13 @@ session:
- claim_id: entity-2
claim_type: entity
claim_value: null
- text_content: gemeente De Wolden
+ text_content: Gemeente De Wolden
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -117,7 +118,7 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 1.0
+ recognition_confidence: 0.95
linking_confidence: 0.0
- claim_id: entity-3
claim_type: entity
@@ -127,8 +128,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[2]/div/div/p[1]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: //div[@class='visitaddress']//p[1]
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -151,8 +152,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[2]/div/div/p[2]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: //div[@class='visitaddress']//p[2]
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -175,8 +176,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[2]/div/div/p[2]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: //div[@class='visitaddress']//p[2]
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -189,57 +190,9 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 0.9
linking_confidence: 0.0
- claim_id: entity-6
- claim_type: entity
- claim_value: null
- text_content: Postbus 20
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[3]/div[2]/div/p[1]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.ADR
- class_uri: schema:PostalAddress
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
- - claim_id: entity-7
- claim_type: entity
- claim_value: null
- text_content: 7920 AA Zuidwolde
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[3]/div[2]/div/p[2]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.ADR
- class_uri: schema:PostalAddress
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
- - claim_id: entity-8
claim_type: entity
claim_value: null
text_content: https://www.dewolden.nl/
@@ -248,7 +201,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/link[@rel='canonical']/@href
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -263,7 +216,7 @@ session:
tei_element: null
recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-9
+ - claim_id: entity-7
claim_type: entity
claim_value: null
text_content: nl
@@ -271,8 +224,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html[@lang='nl']/@lang
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ path: /html/@lang
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -287,126 +240,6 @@ session:
tei_element: null
recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-10
- claim_type: entity
- claim_value: null
- text_content: 'Advies: geen honden op het Dwingelderveld '
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[3]/div[2]/div[2]/div[1]/div/div[1]/h3
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: APP
- hyponym: APP.TIT
- class_uri: crm:E35_Title
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: crm:E35_Title
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-11
- claim_type: entity
- claim_value: null
- text_content: Dwingelderveld
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[3]/div[2]/div[2]/div[1]/div/div[1]/h3
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.NAT
- class_uri: crm:E53_Place
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: crm:E53_Place
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-12
- claim_type: entity
- claim_value: null
- text_content: Provincie Drenthe
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[3]/div[2]/div[2]/div[1]/div/div[2]/div/p
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.GOV
- class_uri: schema:GovernmentOrganization
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-13
- claim_type: entity
- claim_value: null
- text_content: Zuidwolde
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[3]/div[2]/div[2]/div[3]/div/div[2]/div/p
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.9
- linking_confidence: 0.0
- - claim_id: entity-14
- claim_type: entity
- claim_value: null
- text_content: 18 maart 2026
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[2]/div[1]/div[2]/div[9]/a/span[2]
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TMP
- hyponym: TMP.DAB
- class_uri: time:Instant
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
relationship:
- claim_id: rel-1
claim_type: relationship
@@ -417,7 +250,7 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 0.9
@@ -433,7 +266,7 @@ session:
source_claim: false
attributed_to: null
subject:
- entity_id: entity-1
+ entity_id: entity-2
entity_type: GRP.GOV
span_text: Gemeente De Wolden
uri: null
@@ -442,44 +275,7 @@ session:
label: REL.SPA.LOC
direction: FORWARD
object:
- entity_id: entity-3
- entity_type: TOP.ADR
- span_text: Raadhuisstraat 2
- uri: null
- - claim_id: rel-2
- claim_type: relationship
- claim_value: null
- text_content: ''
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: ''
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.9
- relationship_hypernym: REL.SPA
- relationship_hyponym: REL.SPA.CON
- predicate_uris:
- - geo:sfContains
- - crm:P89i_contains
- extraction_confidence: 0.9
- negation: false
- hypothetical: false
- source_claim: false
- attributed_to: null
- subject:
- entity_id: entity-4
- entity_type: TOP.ADR
- span_text: 7921 GD Zuidwolde
- uri: null
- predicate:
- uri: geo:sfContains
- label: REL.SPA.CON
- direction: FORWARD
- object:
- entity_id: entity-13
+ entity_id: entity-5
entity_type: TOP.SET
span_text: Zuidwolde
uri: null
@@ -493,7 +289,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/title
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -508,13 +304,28 @@ session:
provenance:
namespace: glam-ner
path: /html/head/link[@rel='canonical']/@href
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
entity_claims: []
relationship_claims: []
- claim_id: claim-3
+ claim_type: aggregate
+ claim_value: Raadhuisstraat 2, 7921 GD Zuidwolde
+ text_content: Raadhuisstraat 2, 7921 GD Zuidwolde
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: //div[@class='visitaddress']//div[@class='ce-bodytext']
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ entity_claims: []
+ relationship_claims: []
+ - claim_id: claim-4
claim_type: aggregate
claim_value: De officiële website van gemeente De Wolden met informatie over
onze diensten en bestuur. Bij ons regelt u veel zaken eenvoudig online, maar
@@ -529,97 +340,7 @@ session:
provenance:
namespace: glam-ner
path: /html/head/meta[@name='description']/@content
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-4
- claim_type: aggregate
- claim_value: Raadhuisstraat 2, 7921 GD Zuidwolde
- text_content: Raadhuisstraat 2, 7921 GD Zuidwolde
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[2]/div
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-5
- claim_type: aggregate
- claim_value: gemeente@dewolden.nl
- text_content: gemeente@dewolden.nl
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[3]/div[3]/div[2]/div/p[3]/a
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-6
- claim_type: aggregate
- claim_value: 14 0528
- text_content: 14 0528
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/div[4]/div[2]/div[2]/div[1]/div/p/a
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-7
- claim_type: aggregate
- claim_value: https://www.facebook.com/GemDeWolden/
- text_content: https://www.facebook.com/GemDeWolden/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/footer/div/div/ul[2]/li[1]/a/@href
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-8
- claim_type: aggregate
- claim_value: https://www.instagram.com/gemeentedewolden/
- text_content: https://www.instagram.com/gemeentedewolden/
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/footer/div/div/ul[2]/li[2]/a/@href
- timestamp: '2025-12-05T14:30:08.137801+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- entity_claims: []
- relationship_claims: []
- - claim_id: claim-9
- claim_type: aggregate
- claim_value: https://nl.linkedin.com/company/gemeente-de-wolden
- text_content: https://nl.linkedin.com/company/gemeente-de-wolden
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: /html/body/footer/div/div/ul[2]/li[3]/a/@href
- timestamp: '2025-12-05T14:30:08.137801+00:00'
+ timestamp: '2025-12-05T14:34:42.825825+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -628,8 +349,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 14
- claim_count: 9
- relationship_count: 2
+ entity_count: 7
+ claim_count: 4
+ relationship_count: 1
layout_count: 3
errors: *id001
diff --git a/data/nde/enriched/entries/web/0009/werkenbijdeswo.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0009/werkenbijdeswo.nl/annotations_v1.7.0.yaml
index 414db76327..ec891c578f 100644
--- a/data/nde/enriched/entries/web/0009/werkenbijdeswo.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0009/werkenbijdeswo.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T11:53:27.768699+00:00'
+extraction_timestamp: '2025-12-05T14:34:58.905110+00:00'
source_url: https://www.werkenbijdeswo.nl/
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0009/werkenbijdeswo.nl/pages/index.html
session:
- session_id: llm-20251205115308
- started_at: '2025-12-05T11:53:08.797882+00:00'
- completed_at: '2025-12-05T11:53:27.768007+00:00'
+ session_id: llm-20251205143443
+ started_at: '2025-12-05T14:34:43.514768+00:00'
+ completed_at: '2025-12-05T14:34:58.904003+00:00'
agent:
name: unknown
version: 1.0.0
@@ -17,6 +17,24 @@ session:
claims:
layout:
- claim_id: layout-1
+ claim_type: layout
+ claim_value: null
+ text_content: Wil jij werken bij de SWO?
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/title
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: PRIM
+ heading_level: null
+ xpath: /html/head/title
+ parent_claim_id: null
+ - claim_id: layout-2
claim_type: layout
claim_value: null
text_content: Werken voor De Wolden & Hoogeveen
@@ -24,96 +42,77 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: //h1[contains(text(), 'Werken voor De Wolden & Hoogeveen')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: //h1
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: //h1[contains(text(), 'Werken voor De Wolden & Hoogeveen')]
- parent_claim_id: null
- - claim_id: layout-2
- claim_type: layout
- claim_value: null
- text_content: Onze Vacatures
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //h2[contains(text(), 'Onze Vacatures')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- region: DOC.PAR
- semantic_role: PRIM
- heading_level: null
- xpath: //h2[contains(text(), 'Onze Vacatures')]
+ xpath: //h1
parent_claim_id: null
- claim_id: layout-3
claim_type: layout
claim_value: null
- text_content: Bij de SWO werk je aan uitdagende projecten in de op één na grootste
- gemeentelijke organisatie van Drenthe.
+ text_content: Wil jij bijdragen aan een toekomstbestendige organisatie waar
+ je zowel in de stad als op het platteland impact maakt? Bij de SWO werk je
+ aan uitdagende projecten in de op één na grootste gemeentelijke
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: //p[contains(text(), 'Bij de SWO werk je aan uitdagende projecten in
- de op één na grootste gemeentelijke organisatie van Drenthe.')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: //div[@id='P_C_W_8D07C6E64F84FD6CC6850796E97E9FC9_W_387E1830E50E41E98738D9FE08EFD133_Content']/p[2]
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
region: DOC.PAR
semantic_role: PRIM
heading_level: null
- xpath: //p[contains(text(), 'Bij de SWO werk je aan uitdagende projecten in
- de op één na grootste gemeentelijke organisatie van Drenthe.')]
+ xpath: //div[@id='P_C_W_8D07C6E64F84FD6CC6850796E97E9FC9_W_387E1830E50E41E98738D9FE08EFD133_Content']/p[2]
parent_claim_id: null
entity:
- claim_id: entity-1
claim_type: entity
claim_value: null
- text_content: Samenwerkingsorganisatie De Wolden Hoogeveen (SWO)
+ text_content: Samenwerkingsorganisatie De Wolden Hoogeveen
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[3]/@content
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[2]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
hypernym: GRP
- hyponym: GRP.GOV
- class_uri: schema:GovernmentOrganization
+ hyponym: GRP.ASS
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.98
+ recognition_confidence: 0.9
linking_confidence: 0.0
- claim_id: entity-2
claim_type: entity
claim_value: null
- text_content: Samenwerkingsorganisatie De Wolden Hoogeveen (SWO)
+ text_content: SWO
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[3]/@content
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/title/text()
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.NAM
- class_uri: pnv:PersonName
+ hypernym: GRP
+ hyponym: GRP.ASS
+ class_uri: org:FormalOrganization
wikidata_id: null
viaf_id: null
geonames_id: null
@@ -125,50 +124,50 @@ session:
- claim_id: entity-3
claim_type: entity
claim_value: null
- text_content: Wil jij werken bij de SWO?
+ text_content: Hoogeveen
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/title
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[5]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.TIT
- class_uri: crm:E35_Title
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: crm:E35_Title
- tei_element: null
- recognition_confidence: 0.99
- linking_confidence: 0.0
- - claim_id: entity-4
- claim_type: entity
- claim_value: null
- text_content: SWO
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //span[contains(text(), 'Bij de SWO werk je aan uitdagende projecten')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: GRP
- hyponym: GRP.GOV
- class_uri: schema:GovernmentOrganization
+ hypernym: TOP
+ hyponym: TOP.SET
+ class_uri: schema:City
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.97
+ recognition_confidence: 0.9
+ linking_confidence: 0.0
+ - claim_id: entity-4
+ claim_type: entity
+ claim_value: null
+ text_content: De Wolden
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[5]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ hypernym: TOP
+ hyponym: TOP.SET
+ class_uri: schema:City
+ wikidata_id: null
+ viaf_id: null
+ geonames_id: null
+ isil_id: null
+ cidoc_class: null
+ tei_element: null
+ recognition_confidence: 0.9
linking_confidence: 0.0
- claim_id: entity-5
claim_type: entity
@@ -178,71 +177,23 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: //span[contains(text(), 'van Drenthe')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: //div[@id='P_C_W_8D07C6E64F84FD6CC6850796E97E9FC9_W_387E1830E50E41E98738D9FE08EFD133_Content']/p[2]/span[2]/text()
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
+ hyponym: TOP.REG
+ class_uri: schema:AdministrativeArea
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
+ recognition_confidence: 0.9
linking_confidence: 0.0
- claim_id: entity-6
- claim_type: entity
- claim_value: null
- text_content: Hoogeveen
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //span[contains(text(), 'van Hoogeveen en De Wolden')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.96
- linking_confidence: 0.0
- - claim_id: entity-7
- claim_type: entity
- claim_value: null
- text_content: De Wolden
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //span[contains(text(), 'van Hoogeveen en De Wolden')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: TOP
- hyponym: TOP.SET
- class_uri: schema:City
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: null
- tei_element: null
- recognition_confidence: 0.96
- linking_confidence: 0.0
- - claim_id: entity-8
claim_type: entity
claim_value: null
text_content: https://www.werkenbijdeswo.nl/
@@ -250,8 +201,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[8]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -264,103 +215,54 @@ session:
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.99
+ recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-9
+ - claim_id: entity-7
claim_type: entity
claim_value: null
- text_content: Onze Vacatures
+ text_content: nl
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: //h2[contains(text(), 'Onze Vacatures')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/@xml:lang
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: APP
- hyponym: APP.TIT
- class_uri: crm:E35_Title
+ hypernym: THG
+ hyponym: THG.LNG
+ class_uri: crm:E56_Language
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
- cidoc_class: crm:E35_Title
+ cidoc_class: crm:E56_Language
tei_element: null
- recognition_confidence: 0.98
+ recognition_confidence: 1.0
linking_confidence: 0.0
- - claim_id: entity-10
+ - claim_id: entity-8
claim_type: entity
claim_value: null
- text_content: Senior medewerker KCC
+ text_content: Werken bij de SWO
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: //span[contains(text(), 'Senior medewerker KCC')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[13]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
- hypernym: ROL
- hyponym: ROL.OCC
- class_uri: schema:Occupation
+ hypernym: WRK
+ hyponym: WRK.WEB
+ class_uri: schema:WebPage
wikidata_id: null
viaf_id: null
geonames_id: null
isil_id: null
cidoc_class: null
tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
- - claim_id: entity-11
- claim_type: entity
- claim_value: null
- text_content: Berdien Faber
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //strong[contains(text(), 'Berdien Faber')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: AGT
- hyponym: AGT.PER
- class_uri: crm:E21_Person
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: crm:E21_Person
- tei_element: null
- recognition_confidence: 0.95
- linking_confidence: 0.0
- - claim_id: entity-12
- claim_type: entity
- claim_value: null
- text_content: S.K.I.K.
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: //p[contains(text(), 'ontwikkelen door ons unieke trainingsaanbod in
- S.K.I.K.')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 1.0
- hypernym: THG
- hyponym: THG.CON
- class_uri: crm:E28_Conceptual_Object
- wikidata_id: null
- viaf_id: null
- geonames_id: null
- isil_id: null
- cidoc_class: crm:E28_Conceptual_Object
- tei_element: null
recognition_confidence: 0.9
linking_confidence: 0.0
relationship:
@@ -373,44 +275,7 @@ session:
provenance:
namespace: glam-ner
path: ''
- timestamp: '2025-12-05T11:53:27.767321+00:00'
- agent: zai/glm-4.6
- context_convention: GLAM-NER v1.7.0-unified
- confidence: 0.98
- relationship_hypernym: REL.ORG
- relationship_hyponym: REL.ORG.SUB
- predicate_uris:
- - schema:subOrganization
- - wdt:P355
- extraction_confidence: 0.98
- negation: false
- hypothetical: false
- source_claim: false
- attributed_to: null
- subject:
- entity_id: entity-4
- entity_type: GRP.GOV
- span_text: SWO
- uri: null
- predicate:
- uri: schema:subOrganization
- label: REL.ORG.SUB
- direction: FORWARD
- object:
- entity_id: entity-2
- entity_type: GRP.GOV
- span_text: Samenwerkingsorganisatie De Wolden Hoogeveen (SWO)
- uri: null
- - claim_id: rel-2
- claim_type: relationship
- claim_value: null
- text_content: ''
- start_offset: null
- end_offset: null
- provenance:
- namespace: glam-ner
- path: ''
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 0.9
@@ -426,8 +291,8 @@ session:
source_claim: false
attributed_to: null
subject:
- entity_id: entity-4
- entity_type: GRP.GOV
+ entity_id: entity-2
+ entity_type: GRP.ASS
span_text: SWO
uri: null
predicate:
@@ -436,20 +301,96 @@ session:
direction: FORWARD
object:
entity_id: entity-5
- entity_type: TOP.SET
+ entity_type: TOP.REG
span_text: Drenthe
uri: null
- aggregate:
- - claim_id: claim-1
- claim_type: aggregate
- claim_value: Samenwerkingsorganisatie De Wolden Hoogeveen (SWO)
- text_content: Samenwerkingsorganisatie De Wolden Hoogeveen (SWO)
+ - claim_id: rel-2
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[3]/@content
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: ''
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.9
+ relationship_hypernym: REL.SPA
+ relationship_hyponym: REL.SPA.LOC
+ predicate_uris:
+ - crm:P53_has_former_or_current_location
+ - schema:location
+ - wdt:P276
+ extraction_confidence: 0.9
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-2
+ entity_type: GRP.ASS
+ span_text: SWO
+ uri: null
+ predicate:
+ uri: crm:P53_has_former_or_current_location
+ label: REL.SPA.LOC
+ direction: FORWARD
+ object:
+ entity_id: entity-3
+ entity_type: TOP.SET
+ span_text: Hoogeveen
+ uri: null
+ - claim_id: rel-3
+ claim_type: relationship
+ claim_value: null
+ text_content: ''
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: ''
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 0.9
+ relationship_hypernym: REL.SPA
+ relationship_hyponym: REL.SPA.LOC
+ predicate_uris:
+ - crm:P53_has_former_or_current_location
+ - schema:location
+ - wdt:P276
+ extraction_confidence: 0.9
+ negation: false
+ hypothetical: false
+ source_claim: false
+ attributed_to: null
+ subject:
+ entity_id: entity-2
+ entity_type: GRP.ASS
+ span_text: SWO
+ uri: null
+ predicate:
+ uri: crm:P53_has_former_or_current_location
+ label: REL.SPA.LOC
+ direction: FORWARD
+ object:
+ entity_id: entity-4
+ entity_type: TOP.SET
+ span_text: De Wolden
+ uri: null
+ aggregate:
+ - claim_id: claim-1
+ claim_type: aggregate
+ claim_value: Samenwerkingsorganisatie De Wolden Hoogeveen
+ text_content: Samenwerkingsorganisatie De Wolden Hoogeveen
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head/meta[2]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -463,8 +404,8 @@ session:
end_offset: null
provenance:
namespace: glam-ner
- path: //span[contains(text(), 'Bij de SWO werk je aan uitdagende projecten')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/title/text()
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -472,14 +413,20 @@ session:
relationship_claims: []
- claim_id: claim-3
claim_type: aggregate
- claim_value: https://www.werkenbijdeswo.nl/
- text_content: https://www.werkenbijdeswo.nl/
+ claim_value: Wil jij werken in een open en toegankelijke organisatie? Houd jij
+ je persoonlijke ontwikkeling goed bij? Durf jij het (goede) gesprek aan te
+ gaan? Solliciteer dan nu op één van de vacatures van de Samenwerkingsorganisatie
+ De Wolden Hoogeveen (SWO).
+ text_content: Wil jij werken in een open en toegankelijke organisatie? Houd
+ jij je persoonlijke ontwikkeling goed bij? Durf jij het (goede) gesprek aan
+ te gaan? Solliciteer dan nu op één van de vacatures van de Samenwerkingsorganisatie
+ De Wolden Hoogeveen (SWO).
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: /html/head/meta[@property='og:url']/@content
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[2]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -487,17 +434,14 @@ session:
relationship_claims: []
- claim_id: claim-4
claim_type: aggregate
- claim_value: Bij de SWO werk je aan uitdagende projecten in de op één na grootste
- gemeentelijke organisatie van Drenthe.
- text_content: Bij de SWO werk je aan uitdagende projecten in de op één na grootste
- gemeentelijke organisatie van Drenthe.
+ claim_value: https://www.werkenbijdeswo.nl/
+ text_content: https://www.werkenbijdeswo.nl/
start_offset: null
end_offset: null
provenance:
namespace: glam-ner
- path: //p[contains(text(), 'Bij de SWO werk je aan uitdagende projecten in
- de op één na grootste gemeentelijke organisatie van Drenthe.')]
- timestamp: '2025-12-05T11:53:27.767321+00:00'
+ path: /html/head/meta[8]/@content
+ timestamp: '2025-12-05T14:34:58.903325+00:00'
agent: zai/glm-4.6
context_convention: GLAM-NER v1.7.0-unified
confidence: 1.0
@@ -506,8 +450,8 @@ session:
config: {}
errors: &id001 []
summary:
- entity_count: 12
+ entity_count: 8
claim_count: 4
- relationship_count: 2
+ relationship_count: 3
layout_count: 3
errors: *id001
diff --git a/data/nde/enriched/entries/web/0011/gemeente.emmen.nl/annotations_v1.7.0.yaml b/data/nde/enriched/entries/web/0011/gemeente.emmen.nl/annotations_v1.7.0.yaml
index 472f75c4af..82f2283669 100644
--- a/data/nde/enriched/entries/web/0011/gemeente.emmen.nl/annotations_v1.7.0.yaml
+++ b/data/nde/enriched/entries/web/0011/gemeente.emmen.nl/annotations_v1.7.0.yaml
@@ -1,11 +1,11 @@
extraction_version: GLAM-NER v1.7.0
-extraction_timestamp: '2025-12-05T11:53:39.948009+00:00'
+extraction_timestamp: '2025-12-05T14:35:20.059732+00:00'
source_url: http://www.gemeente.emmen.nl
html_file: /Users/kempersc/apps/glam/data/nde/enriched/entries/web/0011/gemeente.emmen.nl/pages/index.html
session:
- session_id: llm-20251205115328
- started_at: '2025-12-05T11:53:28.381075+00:00'
- completed_at: '2025-12-05T11:53:39.947698+00:00'
+ session_id: llm-20251205143459
+ started_at: '2025-12-05T14:34:59.505173+00:00'
+ completed_at: '2025-12-05T14:35:20.059309+00:00'
agent:
name: unknown
version: 1.0.0
@@ -15,57 +15,47 @@ session:
file: null
hash: null
claims:
- layout: []
+ layout:
+ - claim_id: layout-1
+ claim_type: layout
+ claim_value: null
+ text_content: title>Home | Gemeente Emmen
+ start_offset: null
+ end_offset: null
+ provenance:
+ namespace: glam-ner
+ path: /html/head
+ timestamp: '2025-12-05T14:35:20.059071+00:00'
+ agent: zai/glm-4.6
+ context_convention: GLAM-NER v1.7.0-unified
+ confidence: 1.0
+ region: DOC.PAR
+ semantic_role: META
+ heading_level: null
+ xpath: /html/head
+ parent_claim_id: null
+ - claim_id: layout-2
+ claim_type: layout
+ claim_value: null
+ text_content: '
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Kazemattenmuseum op de Afsluitdijk - Kazemattenmuseum
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Kazemattenmuseum op de Afsluitdijk
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Enkele kilometers uit de Friese kust liggen de beroemde kazematten van Kornwerderzand op de Afsluitdijk. Het is de enige plek in Europa waar in de meidagen van 1940 de Duitse Blitzkrieg vastliep. Slechts 225 Nederlandse soldaten wisten zo’n 13.500 Duitsers tegen te houden. Een verhaal om trots op te zijn.
+
+
+
+
+
+
+
+
+
+
+
+
+
Laatste Google Reviews
+
+
+
We visited the Casemate Museum near Harlingen and it was absolutely amazing. The bunkers are in incredible condition – almost like new – and filled with exhibitions and artifacts. There is also a fantastic educational trail with well-presented stories, everything is very clear, informative, and well maintained.
+
+The cannons and weapons displays were really impressive. In the Czech Republic we also have many fortresses, but we have never seen any in such an excellent state as here. There was a huge amount of information to take in, and the whole tour took about 2 hours.
+
+We would definitely like to return in the future and highly recommend this museum to everyone interested in history!
Interesting historic museum about the „Atlantic Wall“ where 220 Durch soldiers defeated 17.000 German sildiers and stopped the advance. Take the Audioguide
Firstly parking is close by and you have to be able to manage stairs 4 flights of across a bridge their is a few places for disabled parking outside the centre. The museum itself is good your able to go inside the bunkers although a lot don’t have much to see mostly text.
A part of Dutch war history we didn't know a lot about, even though dad did fight in this area!
+Good signposted (check website as roadworks at Afsluitdijk do change the route, that's April 2023).
+Very clear map and route in the museum. Started with a film, where people tell their experiences, impressive! As advised, a very good start for exploring the 'kazematten'. Walking through the small corridors, the rooms, you can imagine what war-life must have looked like. In about three hours we were able to read a lot and let it sink in. Lovely little cafe (delicious 'gevulde koeken:' 😀) clean toilets.
Nice small museum not too far from Harlingen. Shame that all posters are in Dutch. Still worth to see. Best way to get there is by car or bicycle. Public transport info from Google maps was completely wrong.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+