add pid

2025-12-02 00:00:45 +01:00 · 2025-12-02 00:00:45 +01:00 · 8ebca2f845
commit 8ebca2f845
parent 4b833d20b2
481 changed files with 4376 additions and 8123 deletions
--- a/data/nde/enriched/entries/0005_Q81181263.yaml
+++ b/data/nde/enriched/entries/0005_Q81181263.yaml
@ -536,18 +536,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:43:58.861472+00:00'
  source_archive: web/0005/aaenhunze.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Gemeente Aa en Hunze
-    source_url: https://www.aaenhunze.nl/
-    retrieved_on: '2025-11-29T13:28:29.517181+00:00'
-    xpath: /html/head/title
-    html_file: web/0005/aaenhunze.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:43:58.860729+00:00'
  - claim_type: address
    claim_value: Spiekersteeg 1
    raw_value: Spiekersteeg 1
@ -628,6 +618,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:43:58.861346+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Aa en Hunze
--- a/data/nde/enriched/entries/0006_Q81181245.yaml
+++ b/data/nde/enriched/entries/0006_Q81181245.yaml
@ -507,18 +507,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:43:59.122650+00:00'
  source_archive: web/0006/borger-odoorn.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Borger-Odoorn
-    source_url: https://www.borger-odoorn.nl/
-    retrieved_on: '2025-11-29T13:30:23.176866+00:00'
-    xpath: /html/head/title
-    html_file: web/0006/borger-odoorn.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:43:59.122129+00:00'
  - claim_type: org_name
    claim_value: default icon
    raw_value: default icon
@ -581,6 +571,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:43:59.122541+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Borger-Odoorn
--- a/data/nde/enriched/entries/0007_Q81181227.yaml
+++ b/data/nde/enriched/entries/0007_Q81181227.yaml
@ -518,18 +518,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:43:59.362549+00:00'
  source_archive: web/0007/coevorden.nl
-  claims_count: 17
+  claims_count: 16
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Coevorden
-    source_url: https://www.coevorden.nl/
-    retrieved_on: '2025-11-29T13:32:08.818759+00:00'
-    xpath: /html/head/title
-    html_file: web/0007/coevorden.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:43:59.361804+00:00'
  - claim_type: org_name
    claim_value: paspoort icon
    raw_value: paspoort icon
@ -692,6 +682,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:43:59.362340+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Coevorden
--- a/data/nde/enriched/entries/0011_Q81181243.yaml
+++ b/data/nde/enriched/entries/0011_Q81181243.yaml
@ -549,18 +549,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:00.017321+00:00'
  source_archive: web/0011/gemeente.emmen.nl
-  claims_count: 32
+  claims_count: 31
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Emmen
-    source_url: http://www.gemeente.emmen.nl
-    retrieved_on: '2025-11-29T14:24:46.985786+00:00'
-    xpath: /html/head/title
-    html_file: web/0011/gemeente.emmen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.016608+00:00'
  - claim_type: org_name
    claim_value: afspraak icon
    raw_value: afspraak icon
@ -871,6 +861,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:00.017183+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Emmen
--- a/data/nde/enriched/entries/0012_Q81181321.yaml
+++ b/data/nde/enriched/entries/0012_Q81181321.yaml
@ -492,18 +492,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:00.530508+00:00'
  source_archive: web/0012/meppel.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Meppel
-    source_url: http://www.meppel.nl
-    retrieved_on: '2025-11-29T14:27:04.292512+00:00'
-    xpath: /html/head/title
-    html_file: web/0012/meppel.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.529951+00:00'
  - claim_type: description_short
    claim_value: De officiële website van Gemeente Meppel – Informatie over wonen,
      werken en leven in Meppel.
@ -586,6 +576,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:00.530413+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Meppel
--- a/data/nde/enriched/entries/0014_Q81181341.yaml
+++ b/data/nde/enriched/entries/0014_Q81181341.yaml
@ -521,7 +521,7 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:00.780426+00:00'
  source_archive: web/0014/noordenveld.nl
-  claims_count: 12
+  claims_count: 9
  claims:
  - claim_type: org_name
    claim_value: Home-NL
@ -553,36 +553,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:00.779541+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.noordenveld.nl/
-    retrieved_on: '2025-11-29T14:24:46.856894+00:00'
-    xpath: /html/body/div[2]/div/footer/div[2]/div/div[3]/ul/li[1]/a/svg/title
-    html_file: web/0014/noordenveld.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.779551+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.noordenveld.nl/
-    retrieved_on: '2025-11-29T14:24:46.856894+00:00'
-    xpath: /html/body/div[2]/div/footer/div[2]/div/div[3]/ul/li[2]/a/svg/title
-    html_file: web/0014/noordenveld.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.779555+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.noordenveld.nl/
-    retrieved_on: '2025-11-29T14:24:46.856894+00:00'
-    xpath: /html/body/div[2]/div/footer/div[2]/div/div[3]/ul/li[3]/a/svg/title
-    html_file: web/0014/noordenveld.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.779559+00:00'
  - claim_type: description_short
    claim_value: Homepagina Nederlands
    raw_value: Homepagina Nederlands
@ -643,6 +613,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:00.780230+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Noordenveld
--- a/data/nde/enriched/entries/0015_Q81181229.yaml
+++ b/data/nde/enriched/entries/0015_Q81181229.yaml
@ -367,18 +367,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:00.887651+00:00'
  source_archive: web/0015/gemeentewesterveld.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Gemeente Westerveld
-    source_url: https://www.gemeentewesterveld.nl/
-    retrieved_on: '2025-11-29T14:24:47.974615+00:00'
-    xpath: /html/head/title
-    html_file: web/0015/gemeentewesterveld.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:00.886185+00:00'
  - claim_type: email
    claim_value: info@gemeentewesterveld.nl
    raw_value: info@gemeentewesterveld.nl
@ -439,6 +429,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:00.887341+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Westerveld
--- a/data/nde/enriched/entries/0016_Q81181377.yaml
+++ b/data/nde/enriched/entries/0016_Q81181377.yaml
@ -557,7 +557,7 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:01.020682+00:00'
  source_archive: web/0016/tynaarlo.nl
-  claims_count: 9
+  claims_count: 8
  claims:
  - claim_type: org_name
    claim_value: Gemeentelijk archief
@ -597,16 +597,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: mailto_link
    extraction_timestamp: '2025-12-01T10:44:01.020346+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer.php?u=https%3A%2F%2Fwww.tynaarlo.nl%2Fbestuur-en-organisatie%2Fgemeentelijk-archief&t=Gemeentelijk+archief
-    raw_value: https://www.facebook.com/sharer.php?u=https%3A%2F%2Fwww.tynaarlo.nl%2Fbestuur-en-organisatie%2Fgemeentelijk-archief&t=Gemeentelijk+archief
-    source_url: https://www.tynaarlo.nl/bestuur-en-organisatie/gemeentelijk-archief
-    retrieved_on: '2025-11-29T14:24:48.197833+00:00'
-    xpath: /html/body/div/main/section[2]/div[2]/div/div/div[1]/a
-    html_file: web/0016/tynaarlo.nl/pages/bestuur-en-organisatie_gemeentelijk-archief.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:01.020515+00:00'
  - claim_type: social_twitter
    claim_value: https://x.com/share?url=https%3A%2F%2Fwww.tynaarlo.nl%2Fbestuur-en-organisatie%2Fgemeentelijk-archief&text=Gemeentelijk+archief
    raw_value: https://x.com/share?url=https%3A%2F%2Fwww.tynaarlo.nl%2Fbestuur-en-organisatie%2Fgemeentelijk-archief&text=Gemeentelijk+archief
@ -657,6 +647,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:01.020542+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Tynaarlo
--- a/data/nde/enriched/entries/0017_harmonium_museum_nederland.yaml
+++ b/data/nde/enriched/entries/0017_harmonium_museum_nederland.yaml
@ -378,18 +378,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:01.302803+00:00'
  source_archive: web/0017/harmoniummuseumnederland.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Harmonium Museum Nederland
-    source_url: https://harmoniummuseumnederland.nl/
-    retrieved_on: '2025-11-29T14:24:50.775403+00:00'
-    xpath: /html/head/title
-    html_file: web/0017/harmoniummuseumnederland.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:01.302081+00:00'
  - claim_type: description_short
    claim_value: Lees alles over de achtergrond en de kerncollectie, die behouden
      bleef, van het Harmonium Museum Nederland, dat helaas is gesloten sinds eind
@ -443,6 +433,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: tel_link
    extraction_timestamp: '2025-12-01T10:44:01.302638+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Harmonium Museum Nederland
--- a/data/nde/enriched/entries/0020_roel_van_der_sleen.yaml
+++ b/data/nde/enriched/entries/0020_roel_van_der_sleen.yaml
@ -375,18 +375,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:01.943174+00:00'
  source_archive: web/0020/historischekringhoogeveen.nl
-  claims_count: 2
+  claims_count: 1
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Historische Kring Hoogeveen
-    source_url: https://www.historischekringhoogeveen.nl/
-    retrieved_on: '2025-11-29T14:24:51.613006+00:00'
-    xpath: /html/head/title
-    html_file: web/0020/historischekringhoogeveen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:01.942281+00:00'
  - claim_type: description_short
    claim_value: Description
    raw_value: Description
@ -397,6 +387,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: meta_description
    extraction_timestamp: '2025-12-01T10:44:01.942394+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historische Kring Hoogeveen
--- a/data/nde/enriched/entries/0022_Q1911968.yaml
+++ b/data/nde/enriched/entries/0022_Q1911968.yaml
@ -565,18 +565,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:02.429976+00:00'
  source_archive: web/0022/smalspoorcentrum.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Industrieel Smalspoor Museum Industrieel Smalspoor Museum
-    source_url: http://www.smalspoorcentrum.nl/
-    retrieved_on: '2025-11-29T14:26:08.048987+00:00'
-    xpath: /html/head/title
-    html_file: web/0022/smalspoorcentrum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:02.428857+00:00'
  - claim_type: org_name
    claim_value: Industrieel Smalspoor Museum
    raw_value: Industrieel Smalspoor Museum
@ -637,6 +627,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:02.429890+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Industrieel Smalspoor Museum
--- a/data/nde/enriched/entries/0023_Q22006174.yaml
+++ b/data/nde/enriched/entries/0023_Q22006174.yaml
@ -602,18 +602,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:02.855034+00:00'
  source_archive: web/0023/miramar-zeemuseum.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Miramar Zeemuseum
-    source_url: https://miramar-zeemuseum.nl/
-    retrieved_on: '2025-11-29T14:26:04.763022+00:00'
-    xpath: /html/head/title
-    html_file: web/0023/miramar-zeemuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:02.853829+00:00'
  - claim_type: description_short
    claim_value: Wat ooit begon met de fascinatie voor een schelp, gevonden op het
      strand van Mallorca, is uitgegroeid tot een waar natuurhistorisch museum in
@ -677,6 +667,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:02.854875+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Miramar Zeemuseum
--- a/data/nde/enriched/entries/0025_Q56461228.yaml
+++ b/data/nde/enriched/entries/0025_Q56461228.yaml
@ -530,18 +530,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:03.370593+00:00'
  source_archive: web/0025/dewemme.nl
-  claims_count: 10
+  claims_count: 9
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Museum de Wemme Zuidwolde
-    source_url: https://www.dewemme.nl/
-    retrieved_on: '2025-11-29T14:26:07.259076+00:00'
-    xpath: /html/head/title
-    html_file: web/0025/dewemme.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:03.369684+00:00'
  - claim_type: org_name
    claim_value: BTC Art
    raw_value: BTC Art - Shine
@ -642,6 +632,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:03.370465+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum De Wemme
--- a/data/nde/enriched/entries/0027_Q19832258.yaml
+++ b/data/nde/enriched/entries/0027_Q19832258.yaml
@ -706,18 +706,8 @@ custodian_name:
 web_claims:
  extraction_timestamp: '2025-12-01T12:24:53.363590+00:00'
  source_archive: web/0027/papierknipmuseum.nl
-  claims_count: 2
+  claims_count: 1
  claims:
-  - claim_type: org_name
-    claim_value: HOME
-    raw_value: HOME
-    source_url: http://www.papierknipmuseum.nl/
-    retrieved_on: ''
-    xpath: /html/head/title
-    html_file: web/0027/papierknipmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:24:53.356977+00:00'
  - claim_type: email
    claim_value: knipkunst@gmail.com
    raw_value: knipkunst@gmail.com
@ -728,3 +718,11 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: mailto_link
    extraction_timestamp: '2025-12-01T12:24:53.362796+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
--- a/data/nde/enriched/entries/0028_aold_daoln.yaml
+++ b/data/nde/enriched/entries/0028_aold_daoln.yaml
@ -372,18 +372,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:04.212422+00:00'
  source_archive: web/0028/aolddaoln.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Aold Daol'n
-    source_url: https://www.aolddaoln.nl/
-    retrieved_on: '2025-11-29T14:26:14.597135+00:00'
-    xpath: /html/head/title
-    html_file: web/0028/aolddaoln.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:04.210876+00:00'
  - claim_type: description_short
    claim_value: Behoud van de geschiedenis en cultuur van Dalen en de naburige dorpen
      door middel van tentoonstellingen, onderzoek en evenementen. Vier samen met
@ -438,6 +428,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:04.212155+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Aold Daol'n
--- a/data/nde/enriched/entries/0029_Q110995917.yaml
+++ b/data/nde/enriched/entries/0029_Q110995917.yaml
@ -549,18 +549,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:04.621248+00:00'
  source_archive: web/0029/aolddaoln.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Aold Daol'n
-    source_url: https://www.aolddaoln.nl/
-    retrieved_on: '2025-11-29T14:26:16.952349+00:00'
-    xpath: /html/head/title
-    html_file: web/0029/aolddaoln.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:04.620027+00:00'
  - claim_type: description_short
    claim_value: Behoud van de geschiedenis en cultuur van Dalen en de naburige dorpen
      door middel van tentoonstellingen, onderzoek en evenementen. Vier samen met
@ -615,6 +605,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:04.621081+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museummolen Jan Pol
--- a/data/nde/enriched/entries/0037_Q1345886.yaml
+++ b/data/nde/enriched/entries/0037_Q1345886.yaml
@ -717,18 +717,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:05.753578+00:00'
  source_archive: web/0037/klompenmuseum.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Internationaal Klompenmuseum Eelde
-    source_url: http://www.klompenmuseum.nl/
-    retrieved_on: '2025-11-29T14:29:05.952480+00:00'
-    xpath: /html/head/title
-    html_file: web/0037/klompenmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:05.752826+00:00'
  - claim_type: description_short
    claim_value: 'Internationaal Klompenmuseum Tentoonstelling 2025: Houten Schoeisel
      Festival Bekijk onze virtuele tour Geopend: 28 maart 2026 t/m 1 november 2026,
@ -817,6 +807,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:05.753486+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Internationaal Klompenmuseum
--- a/data/nde/enriched/entries/0039_Q108369683.yaml
+++ b/data/nde/enriched/entries/0039_Q108369683.yaml
@ -485,18 +485,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:06.586496+00:00'
  source_archive: web/0039/oudmeppel.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Stichting Oud Meppel
-    source_url: https://www.oudmeppel.nl/
-    retrieved_on: '2025-11-29T14:32:06.738895+00:00'
-    xpath: /html/head/title
-    html_file: web/0039/oudmeppel.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:06.585102+00:00'
  - claim_type: description_short
    claim_value: "Welkom bij Oud Meppel    Overzicht   \nActiviteiten \nDiavoorstellingen\
      \ \nTentoonstellingen \nStadswandelingen \nWerkgroepen \nVerkoop \nDiversen\
@ -563,6 +553,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:06.586287+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Oud Meppel
--- a/data/nde/enriched/entries/0041_asser_historische_vereniging.yaml
+++ b/data/nde/enriched/entries/0041_asser_historische_vereniging.yaml
@ -350,18 +350,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:07.100160+00:00'
  source_archive: web/0041/ahvassen.nl
-  claims_count: 4
+  claims_count: 3
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://ahvassen.nl/
-    retrieved_on: '2025-11-29T14:29:15.708064+00:00'
-    xpath: /html/head/title
-    html_file: web/0041/ahvassen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:07.099272+00:00'
  - claim_type: description_short
    claim_value: Asser Historische Vereniging
    raw_value: Asser Historische Vereniging
@ -392,6 +382,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:07.099994+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Asser Historische Vereniging
--- a/data/nde/enriched/entries/0042_asser_historische_vereniging_2.yaml
+++ b/data/nde/enriched/entries/0042_asser_historische_vereniging_2.yaml
@ -347,18 +347,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:07.171284+00:00'
  source_archive: web/0042/drentsehistorischevereniging.nl
-  claims_count: 4
+  claims_count: 3
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://drentsehistorischevereniging.nl/
-    retrieved_on: '2025-11-29T14:29:17.235710+00:00'
-    xpath: /html/head/title
-    html_file: web/0042/drentsehistorischevereniging.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:07.170786+00:00'
  - claim_type: org_name
    claim_value: Drentse Historische Vereniging
    raw_value: Drentse Historische Vereniging
@ -389,6 +379,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:07.171165+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Drentse Historische Vereniging
--- a/data/nde/enriched/entries/0043_historische_vereniging_gasselte.yaml
+++ b/data/nde/enriched/entries/0043_historische_vereniging_gasselte.yaml
@ -355,7 +355,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:07.584213+00:00'
  source_archive: web/0043/archief-optspoor.nl
-  claims_count: 2
+  claims_count: 1
  claims:
  - claim_type: org_name
    claim_value: Historische vereniging der gemeente Gasselte
@ -367,16 +367,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:07.583755+00:00'
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://archief-optspoor.nl/
-    retrieved_on: '2025-11-29T14:29:26.053674+00:00'
-    xpath: /html/body/div[1]/div/div/div/div/main/article/header/h1
-    html_file: web/0043/archief-optspoor.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:07.584126+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historische vereniging der gemeente Gasselte
--- a/data/nde/enriched/entries/0047_Q30277559.yaml
+++ b/data/nde/enriched/entries/0047_Q30277559.yaml
@ -566,7 +566,7 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:07.769543+00:00'
  source_archive: web/0047/hetflevolandsarchief.nl
-  claims_count: 4
+  claims_count: 3
  claims:
  - claim_type: org_name
    claim_value: Het Flevolands Archief
@ -598,16 +598,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:07.769111+00:00'
-  - claim_type: org_name
-    claim_value: Nieuws
-    raw_value: Nieuws
-    source_url: https://www.hetflevolandsarchief.nl/
-    retrieved_on: '2025-11-29T14:29:20.248807+00:00'
-    xpath: /html/body/div[2]/main/div[6]/div/div/div/h1
-    html_file: web/0047/hetflevolandsarchief.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:07.769239+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Het Flevolands Archief
--- a/data/nde/enriched/entries/0069_Q13137174.yaml
+++ b/data/nde/enriched/entries/0069_Q13137174.yaml
@ -727,18 +727,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:13.342313+00:00'
  source_archive: web/0069/museumfederatiefryslan.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Museumfederatie Fryslân
-    source_url: https://www.museumfederatiefryslan.nl/
-    retrieved_on: '2025-11-29T14:34:37.779528+00:00'
-    xpath: /html/head/title
-    html_file: web/0069/museumfederatiefryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:13.341754+00:00'
  - claim_type: description_short
    claim_value: Museumfederatie Fryslân staat voor het toegankelijk maken en behouden
      van het erfgoed in Friesland op een zo hoog mogelijk niveau. Samenwerken op
@ -793,6 +783,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:13.342260+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museumfederatie Fryslân
--- a/data/nde/enriched/entries/0070_Q17517652.yaml
+++ b/data/nde/enriched/entries/0070_Q17517652.yaml
@ -461,7 +461,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:13.420511+00:00'
  source_archive: web/0070/kiekhuus.nl
-  claims_count: 8
+  claims_count: 6
  claims:
  - claim_type: org_name
    claim_value: Terug in de tijd
@ -495,26 +495,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: og_site_name
    extraction_timestamp: '2025-12-01T10:44:13.420097+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer.php?t=Terug in de tijd&u=https://www.kiekhuus.nl/
-    raw_value: https://www.facebook.com/sharer.php?t=Terug in de tijd&u=https://www.kiekhuus.nl/
-    source_url: http://www.kiekhuus.nl
-    retrieved_on: '2025-11-29T14:32:53.893434+00:00'
-    xpath: /html/body/div[2]/div[2]/div/section/div/div/div[1]/div/div/div/a[1]
-    html_file: web/0070/kiekhuus.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:13.420372+00:00'
-  - claim_type: social_twitter
-    claim_value: https://twitter.com/intent/tweet?text=Terug in de tijd&url=https://www.kiekhuus.nl/&via=
-    raw_value: https://twitter.com/intent/tweet?text=Terug in de tijd&url=https://www.kiekhuus.nl/&via=
-    source_url: http://www.kiekhuus.nl
-    retrieved_on: '2025-11-29T14:32:53.893434+00:00'
-    xpath: /html/body/div[2]/div[2]/div/section/div/div/div[1]/div/div/div/a[2]
-    html_file: web/0070/kiekhuus.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:13.420378+00:00'
  - claim_type: social_facebook
    claim_value: https://www.facebook.com/kiekhuus/
    raw_value: https://www.facebook.com/kiekhuus/
@ -545,6 +525,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:13.420399+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: '''t Kiekhuus'
--- a/data/nde/enriched/entries/0072_Q3457274.yaml
+++ b/data/nde/enriched/entries/0072_Q3457274.yaml
@ -791,18 +791,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:13.941510+00:00'
  source_archive: web/0072/museumdrachten.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Museum Dr8888
-    source_url: http://www.museumdrachten.nl
-    retrieved_on: '2025-11-29T14:33:08.640521+00:00'
-    xpath: /html/head/title
-    html_file: web/0072/museumdrachten.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:13.940327+00:00'
  - claim_type: org_name
    claim_value: Museum Dr8888
    raw_value: Museum Dr8888
@ -853,6 +843,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:13.941354+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Drachten
--- a/data/nde/enriched/entries/0080_Q1942351.yaml
+++ b/data/nde/enriched/entries/0080_Q1942351.yaml
@ -702,7 +702,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:16.206454+00:00'
  source_archive: web/0080/damshus.nl
-  claims_count: 6
+  claims_count: 5
  claims:
  - claim_type: org_name
    claim_value: It Damshûs
@ -756,16 +756,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:16.206249+00:00'
-  - claim_type: org_name
-    claim_value: Oproep
-    raw_value: Oproep
-    source_url: https://www.damshus.nl/
-    retrieved_on: '2025-11-29T14:36:55.509152+00:00'
-    xpath: /html/body/div[1]/div/div/div/article/div/div/div/div[2]/div/div/div[1]/div/h1
-    html_file: web/0080/damshus.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:16.206329+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting "It Damshûs"
--- a/data/nde/enriched/entries/0082_Q2201887.yaml
+++ b/data/nde/enriched/entries/0082_Q2201887.yaml
@ -946,7 +946,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:16.964027+00:00'
  source_archive: web/0082/observeum.nl
-  claims_count: 7
+  claims_count: 5
  claims:
  - claim_type: org_name
    claim_value: Museum & Sterrenwacht Burgum
@ -980,16 +980,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:16.963804+00:00'
-  - claim_type: social_facebook
-    claim_value: http://www.facebook.com/sharer.php?u=https://www.observeum.nl/&t=Home
-    raw_value: http://www.facebook.com/sharer.php?u=https://www.observeum.nl/&t=Home
-    source_url: https://www.observeum.nl/
-    retrieved_on: '2025-11-29T14:36:01.804617+00:00'
-    xpath: /html/body/div/div[2]/div[2]/div[2]/div/div[2]/div[41]/div/a[1]
-    html_file: web/0082/observeum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:16.963824+00:00'
  - claim_type: social_twitter
    claim_value: https://x.com/share?text=Home&url=https%3A%2F%2Fwww.observeum.nl%2F
    raw_value: https://x.com/share?text=Home&url=https%3A%2F%2Fwww.observeum.nl%2F
@ -1000,16 +990,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:16.963828+00:00'
-  - claim_type: social_linkedin
-    claim_value: http://www.linkedin.com/shareArticle?mini=true&url=https://www.observeum.nl/&title=Home
-    raw_value: http://www.linkedin.com/shareArticle?mini=true&url=https://www.observeum.nl/&title=Home
-    source_url: https://www.observeum.nl/
-    retrieved_on: '2025-11-29T14:36:01.804617+00:00'
-    xpath: /html/body/div/div[2]/div[2]/div[2]/div/div[2]/div[41]/div/a[4]
-    html_file: web/0082/observeum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:16.963834+00:00'
  - claim_type: org_name
    claim_value: Museum en Sterrenwacht Burgum
    raw_value: Museum en Sterrenwacht Burgum
@ -1020,6 +1000,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:16.963894+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Observeum
--- a/data/nde/enriched/entries/0086_Q13137164.yaml
+++ b/data/nde/enriched/entries/0086_Q13137164.yaml
@ -651,18 +651,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:18.289120+00:00'
  source_archive: web/0086/dekemastate.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Dekema State
-    source_url: https://dekemastate.nl/
-    retrieved_on: '2025-11-29T14:38:06.707912+00:00'
-    xpath: /html/head/title
-    html_file: web/0086/dekemastate.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:18.288285+00:00'
  - claim_type: org_name
    claim_value: Klik om het zoekinvoerveld te openen
    raw_value: Klik om het zoekinvoerveld te openen
@ -735,6 +725,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:18.288910+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Landgoed Dekema State / Dekema State
--- a/data/nde/enriched/entries/0093_Q81181219.yaml
+++ b/data/nde/enriched/entries/0093_Q81181219.yaml
@ -525,18 +525,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:19.908909+00:00'
  source_archive: web/0093/achtkarspelen.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Achtkarspelen
-    source_url: http://www.achtkarspelen.nl
-    retrieved_on: '2025-11-29T14:36:05.489613+00:00'
-    xpath: /html/head/title
-    html_file: web/0093/achtkarspelen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:19.908104+00:00'
  - claim_type: org_name
    claim_value: Loading...
    raw_value: Loading...
@ -599,6 +589,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:19.908727+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Achtkarspelen
--- a/data/nde/enriched/entries/0095_Q81181251.yaml
+++ b/data/nde/enriched/entries/0095_Q81181251.yaml
@ -360,7 +360,7 @@ custodian_name:
 web_claims:
  extraction_timestamp: '2025-12-01T12:25:12.247324+00:00'
  source_archive: web/0095/noardeast-fryslan.nl
-  claims_count: 12
+  claims_count: 9
  claims:
  - claim_type: org_name
    claim_value: Homepage Noardeast-Fryslân
@ -392,36 +392,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T12:25:12.245246+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0095/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.245258+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0095/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.245268+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0095/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.245278+00:00'
  - claim_type: description_short
    claim_value: Homepage Noardeast-Fryslân
    raw_value: Homepage Noardeast-Fryslân
@ -482,6 +452,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T12:25:12.246132+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 temporal_extent:
  begin_of_the_begin: null
  end_of_the_begin: null
--- a/data/nde/enriched/entries/0099_Q81181286.yaml
+++ b/data/nde/enriched/entries/0099_Q81181286.yaml
@ -468,7 +468,7 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:20.689774+00:00'
  source_archive: web/0099/heerenveen.nl
-  claims_count: 29
+  claims_count: 25
  claims:
  - claim_type: org_name
    claim_value: Alles over gemeente Heerenveen
@ -480,16 +480,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:20.688647+00:00'
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://www.heerenveen.nl
-    retrieved_on: '2025-11-29T14:37:26.166072+00:00'
-    xpath: /html/body/header/nav/ul/li[1]/a/svg/title
-    html_file: web/0099/heerenveen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.688660+00:00'
  - claim_type: org_name
    claim_value: A-Z
    raw_value: A-Z
@ -530,16 +520,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:20.688677+00:00'
-  - claim_type: org_name
-    claim_value: Zoeken
-    raw_value: Zoeken
-    source_url: https://www.heerenveen.nl
-    retrieved_on: '2025-11-29T14:37:26.166072+00:00'
-    xpath: /html/body/header/nav/div[2]/form/div/svg/title
-    html_file: web/0099/heerenveen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.688700+00:00'
  - claim_type: org_name
    claim_value: icon_verkiezingen
    raw_value: icon_verkiezingen
@ -590,16 +570,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:20.688718+00:00'
-  - claim_type: org_name
-    claim_value: Contact
-    raw_value: Contact
-    source_url: https://www.heerenveen.nl
-    retrieved_on: '2025-11-29T14:37:26.166072+00:00'
-    xpath: /html/body/header/nav/div[3]/nav/a[6]/div/svg/title
-    html_file: web/0099/heerenveen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.688722+00:00'
  - claim_type: org_name
    claim_value: Klok
    raw_value: Klok
@ -650,16 +620,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:20.688745+00:00'
-  - claim_type: org_name
-    claim_value: Nieuws
-    raw_value: Nieuws
-    source_url: https://www.heerenveen.nl
-    retrieved_on: '2025-11-29T14:37:26.166072+00:00'
-    xpath: /html/body/main/div[3]/div[1]/div[1]/svg/title
-    html_file: web/0099/heerenveen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.688759+00:00'
  - claim_type: org_name
    claim_value: LinkedIn profiel van Gemeente Heerenveen
    raw_value: LinkedIn profiel van Gemeente Heerenveen
@ -762,6 +722,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:20.689444+00:00'
+  removed_invalid_claims:
+  - removed_count: 4
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Heerenveen
--- a/data/nde/enriched/entries/0101_Q81181296.yaml
+++ b/data/nde/enriched/entries/0101_Q81181296.yaml
@ -362,7 +362,7 @@ custodian_name:
 web_claims:
  extraction_timestamp: '2025-12-01T12:25:12.500058+00:00'
  source_archive: web/0101/noardeast-fryslan.nl
-  claims_count: 12
+  claims_count: 9
  claims:
  - claim_type: org_name
    claim_value: Homepage Noardeast-Fryslân
@ -394,36 +394,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T12:25:12.498580+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0101/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.498591+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0101/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.498601+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.noardeast-fryslan.nl/streekarchief
-    retrieved_on: ''
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0101/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.498611+00:00'
  - claim_type: description_short
    claim_value: Homepage Noardeast-Fryslân
    raw_value: Homepage Noardeast-Fryslân
@ -484,6 +454,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T12:25:12.499739+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 temporal_extent:
  begin_of_the_begin: null
  end_of_the_begin: null
--- a/data/nde/enriched/entries/0102_Q121225319.yaml
+++ b/data/nde/enriched/entries/0102_Q121225319.yaml
@ -572,7 +572,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:20.875194+00:00'
  source_archive: web/0102/noardeast-fryslan.nl
-  claims_count: 12
+  claims_count: 9
  claims:
  - claim_type: org_name
    claim_value: Homepage Noardeast-Fryslân
@ -604,36 +604,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:20.874548+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.noardeast-fryslan.nl/
-    retrieved_on: '2025-11-29T14:37:55.770920+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0102/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.874553+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.noardeast-fryslan.nl/
-    retrieved_on: '2025-11-29T14:37:55.770920+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0102/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.874558+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.noardeast-fryslan.nl/
-    retrieved_on: '2025-11-29T14:37:55.770920+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0102/noardeast-fryslan.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.874562+00:00'
  - claim_type: description_short
    claim_value: Homepage Noardeast-Fryslân
    raw_value: Homepage Noardeast-Fryslân
@ -694,6 +664,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:20.875058+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Streekarchief Noardeast-Fryslân
--- a/data/nde/enriched/entries/0103_Q81181358.yaml
+++ b/data/nde/enriched/entries/0103_Q81181358.yaml
@ -299,18 +299,8 @@ custodian_name:
 web_claims:
  extraction_timestamp: '2025-12-01T12:25:12.598702+00:00'
  source_archive: web/0103/documentatiestichting.nl
-  claims_count: 3
+  claims_count: 2
  claims:
-  - claim_type: org_name
-    claim_value: Contact
-    raw_value: Contact – Documentatiestichting Leeuwarderadeel
-    source_url: http://www.documentatiestichting.nl/contact/
-    retrieved_on: ''
-    xpath: /html/head/title
-    html_file: web/0103/documentatiestichting.nl/rendered.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T12:25:12.597880+00:00'
  - claim_type: email
    claim_value: documentatiestichting@gmail.com
    raw_value: documentatiestichting@gmail.com
@ -331,3 +321,11 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: mailto_link
    extraction_timestamp: '2025-12-01T12:25:12.598321+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
--- a/data/nde/enriched/entries/0104_Q2754844.yaml
+++ b/data/nde/enriched/entries/0104_Q2754844.yaml
@ -904,18 +904,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:20.991233+00:00'
  source_archive: web/0104/historischcentrumleeuwarden.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Historisch Centrum Leeuwarden
-    source_url: http://historischcentrumleeuwarden.nl
-    retrieved_on: '2025-11-29T14:38:07.710368+00:00'
-    xpath: /html/head/title
-    html_file: web/0104/historischcentrumleeuwarden.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:20.990803+00:00'
  - claim_type: description_short
    claim_value: Het Historisch Centrum Leeuwarden (HCL) is het informatie- en activiteitencentrum
      voor de geschiedenis van Leeuwarden en omgeving.
@ -988,6 +978,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:20.991168+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historisch Centrum Leeuwarden
--- a/data/nde/enriched/entries/0107_Q81181235.yaml
+++ b/data/nde/enriched/entries/0107_Q81181235.yaml
@ -358,18 +358,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:21.184233+00:00'
  source_archive: web/0107/smallingerland.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Smallingerland
-    source_url: https://www.smallingerland.nl/
-    retrieved_on: '2025-11-29T14:38:08.667336+00:00'
-    xpath: /html/head/title
-    html_file: web/0107/smallingerland.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:21.183016+00:00'
  - claim_type: email
    claim_value: gemeente@smallingerland.nl
    raw_value: gemeente@smallingerland.nl
@ -430,6 +420,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:21.184035+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeente Smallingerland
--- a/data/nde/enriched/entries/0109_Q81181393.yaml
+++ b/data/nde/enriched/entries/0109_Q81181393.yaml
@ -388,18 +388,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:21.633706+00:00'
  source_archive: web/0109/terschelling.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Terschelling
-    source_url: https://www.terschelling.nl/
-    retrieved_on: '2025-11-29T14:38:09.179167+00:00'
-    xpath: /html/head/title
-    html_file: web/0109/terschelling.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:21.632596+00:00'
  - claim_type: org_name
    claim_value: Toegankelijkheid
    raw_value: Toegankelijkheid
@ -470,6 +460,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:21.633521+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Terschelling
--- a/data/nde/enriched/entries/0110_Q81181206.yaml
+++ b/data/nde/enriched/entries/0110_Q81181206.yaml
@ -518,18 +518,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:21.752348+00:00'
  source_archive: web/0110/t-diel.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Tytsjerksteradiel
-    source_url: http://www.t-diel.nl
-    retrieved_on: '2025-11-29T14:38:09.847466+00:00'
-    xpath: /html/head/title
-    html_file: web/0110/t-diel.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:21.751276+00:00'
  - claim_type: org_name
    claim_value: Loading...
    raw_value: Loading...
@ -592,6 +582,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:21.751956+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Tytsjerksteradiel
--- a/data/nde/enriched/entries/0111_Q81181373.yaml
+++ b/data/nde/enriched/entries/0111_Q81181373.yaml
@ -538,18 +538,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:21.884305+00:00'
  source_archive: web/0111/vlieland.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Vlieland
-    source_url: http://www.vlieland.nl
-    retrieved_on: '2025-11-29T14:38:10.812158+00:00'
-    xpath: /html/head/title
-    html_file: web/0111/vlieland.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:21.883565+00:00'
  - claim_type: org_name
    claim_value: Toegankelijkheid
    raw_value: Toegankelijkheid
@ -620,6 +610,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:21.884109+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Vlieland
--- a/data/nde/enriched/entries/0115_Q13136222.yaml
+++ b/data/nde/enriched/entries/0115_Q13136222.yaml
@ -506,18 +506,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:23.119742+00:00'
  source_archive: web/0115/ijstijdenmuseum.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - ijstijdenmuseum
-    source_url: https://www.ijstijdenmuseum.nl/
-    retrieved_on: '2025-11-29T14:38:51.284331+00:00'
-    xpath: /html/head/title
-    html_file: web/0115/ijstijdenmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:23.119152+00:00'
  - claim_type: description_short
    claim_value: De IJstijden in deze streken In het IJstijdenmuseum in Buitenpost
      wordt het boeiende verhaal verteld van de twee laatste IJstijden. Deze hebben
@ -572,6 +562,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:23.119650+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: IJstijdenmuseum
--- a/data/nde/enriched/entries/0122_Q12013196.yaml
+++ b/data/nde/enriched/entries/0122_Q12013196.yaml
@ -1209,18 +1209,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:24.410901+00:00'
  source_archive: web/0122/museumbelvedere.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Museum Belvédère
-    source_url: https://www.museumbelvedere.nl/
-    retrieved_on: '2025-11-29T15:18:22.314806+00:00'
-    xpath: /html/head/title
-    html_file: web/0122/museumbelvedere.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:24.410285+00:00'
  - claim_type: email
    claim_value: info@museumbelvedere.nl
    raw_value: info@museumbelvedere.nl
@ -1271,6 +1261,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:24.410817+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Museum Belvédère
--- a/data/nde/enriched/entries/0124_museum_oold_ark_korenmolen_de_weyert.yaml
+++ b/data/nde/enriched/entries/0124_museum_oold_ark_korenmolen_de_weyert.yaml
@ -184,18 +184,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:24.984364+00:00'
  source_archive: web/0124/museumenmolenmakkinga.nl
-  claims_count: 2
+  claims_count: 1
  claims:
-  - claim_type: org_name
-    claim_value: Nieuws
-    raw_value: Nieuws
-    source_url: https://www.museumenmolenmakkinga.nl/
-    retrieved_on: '2025-11-29T14:39:27.748370+00:00'
-    xpath: /html/head/title
-    html_file: web/0124/museumenmolenmakkinga.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:24.984075+00:00'
  - claim_type: social_facebook
    claim_value: https://www.facebook.com/Museum-en-Molen-Makkinga-686046891528133
    raw_value: https://www.facebook.com/Museum-en-Molen-Makkinga-686046891528133
@ -206,6 +196,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:24.984314+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Korenmolen "De Weyert"
--- a/data/nde/enriched/entries/0125_Q13137340.yaml
+++ b/data/nde/enriched/entries/0125_Q13137340.yaml
@ -550,18 +550,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:25.116518+00:00'
  source_archive: web/0125/museumenmolenmakkinga.nl
-  claims_count: 2
+  claims_count: 1
  claims:
-  - claim_type: org_name
-    claim_value: Nieuws
-    raw_value: Nieuws
-    source_url: https://www.museumenmolenmakkinga.nl/
-    retrieved_on: '2025-11-29T14:54:51.730430+00:00'
-    xpath: /html/head/title
-    html_file: web/0125/museumenmolenmakkinga.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:25.116241+00:00'
  - claim_type: social_facebook
    claim_value: https://www.facebook.com/Museum-en-Molen-Makkinga-686046891528133
    raw_value: https://www.facebook.com/Museum-en-Molen-Makkinga-686046891528133
@ -572,6 +562,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:25.116469+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Oold Ark
--- a/data/nde/enriched/entries/0126_Q13137168.yaml
+++ b/data/nde/enriched/entries/0126_Q13137168.yaml
@ -641,18 +641,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:25.214070+00:00'
  source_archive: web/0126/museumsloten.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://museumsloten.nl/
-    retrieved_on: '2025-11-29T14:54:52.407703+00:00'
-    xpath: /html/head/title
-    html_file: web/0126/museumsloten.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:25.213029+00:00'
  - claim_type: description_short
    claim_value: Ontdek Sloten, de kleinste van de Friese 11 steden, in Museum Sloten,
      waar toverlantaarns de geschiedenis vertellen, en boek meteen je tickets.
@ -705,6 +695,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:25.213909+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Sloten
--- a/data/nde/enriched/entries/0131_Q81181312.yaml
+++ b/data/nde/enriched/entries/0131_Q81181312.yaml
@ -508,18 +508,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:26.659287+00:00'
  source_archive: web/0131/fryslan.frl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Fryslan
-    source_url: https://www.fryslan.frl/
-    retrieved_on: '2025-11-29T15:14:45.171069+00:00'
-    xpath: /html/head/title
-    html_file: web/0131/fryslan.frl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:26.657906+00:00'
  - claim_type: org_name
    claim_value: Fryslan
    raw_value: Fryslan
@ -580,6 +570,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:26.658955+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Provincie Fryslân
--- a/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml
+++ b/data/nde/enriched/entries/0139_de_hollandse_cirkel.yaml
@ -182,7 +182,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:27.725393+00:00'
  source_archive: web/0139/hollandsecirkel.nl
-  claims_count: 4
+  claims_count: 3
  claims:
  - claim_type: org_name
    claim_value: Stichting de Hollandse Cirkel
@ -214,16 +214,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: mailto_link
    extraction_timestamp: '2025-12-01T10:44:27.725070+00:00'
-  - claim_type: org_name
-    claim_value: Nieuws
-    raw_value: Nieuws
-    source_url: https://www.kadaster.nl/
-    retrieved_on: ''
-    xpath: /html/body/div/div/div/div/article/div/div/div/div[5]/div[1]/div/div/div/h1
-    html_file: web/0139/hollandsecirkel.nl/mirror/hollandsecirkel.nl/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:27.725271+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting De Hollandse Cirkel
--- a/data/nde/enriched/entries/0140_Q17595943.yaml
+++ b/data/nde/enriched/entries/0140_Q17595943.yaml
@ -620,18 +620,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:27.849066+00:00'
  source_archive: web/0140/archief.gazelle.nl
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Zoeken
-    raw_value: Zoeken - Gazelle
-    source_url: https://archief.gazelle.nl/
-    retrieved_on: '2025-11-29T15:21:15.145560+00:00'
-    xpath: /html/head/title
-    html_file: web/0140/archief.gazelle.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:27.847294+00:00'
  - claim_type: social_facebook
    claim_value: https://www.facebook.com/KoninklijkeGazelle
    raw_value: https://www.facebook.com/KoninklijkeGazelle
@ -672,6 +662,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:27.848728+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Koninklijke Gazelle
--- a/data/nde/enriched/entries/0143_Q1127079.yaml
+++ b/data/nde/enriched/entries/0143_Q1127079.yaml
@ -1287,18 +1287,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:28.142443+00:00'
  source_archive: web/0143/museumhetvalkhof.nl
-  claims_count: 2
+  claims_count: 1
  claims:
-  - claim_type: org_name
-    claim_value: home
-    raw_value: home - Valkhof Museum
-    source_url: http://www.museumhetvalkhof.nl
-    retrieved_on: '2025-11-29T15:21:15.209526+00:00'
-    xpath: /html/head/title
-    html_file: web/0143/museumhetvalkhof.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.142145+00:00'
  - claim_type: org_name
    claim_value: Valkhof Museum
    raw_value: Valkhof Museum
@ -1309,6 +1299,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: og_site_name
    extraction_timestamp: '2025-12-01T10:44:28.142360+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Het Valkhof
--- a/data/nde/enriched/entries/0144_Q2710899.yaml
+++ b/data/nde/enriched/entries/0144_Q2710899.yaml
@ -873,18 +873,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:28.228638+00:00'
  source_archive: web/0144/nationaalonderduikmuseum.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Nationaal onderduikmuseum
-    source_url: https://nationaalonderduikmuseum.nl/
-    retrieved_on: ''
-    xpath: /html/head/title
-    html_file: web/0144/nationaalonderduikmuseum.nl/mirror/nationaalonderduikmuseum.nl/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.227592+00:00'
  - claim_type: org_name
    claim_value: Nationaal onderduikmuseum -
    raw_value: Nationaal onderduikmuseum -
@ -965,6 +955,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:28.228541+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Nationaal Onderduikmuseum
--- a/data/nde/enriched/entries/0145_Q2654815.yaml
+++ b/data/nde/enriched/entries/0145_Q2654815.yaml
@ -711,7 +711,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:28.300061+00:00'
  source_archive: web/0145/antonpieckmuseum.nl
-  claims_count: 9
+  claims_count: 7
  claims:
  - claim_type: org_name
    claim_value: Anton Pieck Museum
@ -733,26 +733,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:28.298463+00:00'
-  - claim_type: org_name
-    claim_value: Vorige
-    raw_value: Vorige
-    source_url: https://www.antonpieckmuseum.nl/
-    retrieved_on: ''
-    xpath: /html/body/div[1]/div/div[1]/div/div[1]/a[1]/svg/title
-    html_file: web/0145/antonpieckmuseum.nl/mirror/www.antonpieckmuseum.nl/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.298469+00:00'
-  - claim_type: org_name
-    claim_value: Volgende
-    raw_value: Volgende
-    source_url: https://www.antonpieckmuseum.nl/
-    retrieved_on: ''
-    xpath: /html/body/div[1]/div/div[1]/div/div[1]/a[2]/svg/title
-    html_file: web/0145/antonpieckmuseum.nl/mirror/www.antonpieckmuseum.nl/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.298473+00:00'
  - claim_type: org_name
    claim_value: Scroll naar bovenzijde
    raw_value: Scroll naar bovenzijde
@ -803,6 +783,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:28.299741+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Anton Pieck Museum
--- a/data/nde/enriched/entries/0146_Q1663974.yaml
+++ b/data/nde/enriched/entries/0146_Q1663974.yaml
@ -646,18 +646,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:28.483481+00:00'
  source_archive: web/0146/tua.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Theologische Universiteit Apeldoorn
-    source_url: http://www.tua.nl
-    retrieved_on: '2025-11-29T15:21:15.976954+00:00'
-    xpath: /html/head/title
-    html_file: web/0146/tua.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.482634+00:00'
  - claim_type: org_name
    claim_value: Theologische Universiteit Apeldoorn
    raw_value: Theologische Universiteit Apeldoorn
@ -738,6 +728,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:28.483392+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Theologische Universiteit Apeldoorn
--- a/data/nde/enriched/entries/0149_Q98894593.yaml
+++ b/data/nde/enriched/entries/0149_Q98894593.yaml
@ -568,18 +568,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:28.738219+00:00'
  source_archive: web/0149/cvz7aar.nl
-  claims_count: 3
+  claims_count: 2
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Cultuurhistorische Vereniging Zevenaar (CVZ) (powered by e-captain.nl)
-    source_url: https://www.cvz7aar.nl
-    retrieved_on: '2025-11-29T15:21:18.588342+00:00'
-    xpath: /html/head/title
-    html_file: web/0149/cvz7aar.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:28.737638+00:00'
  - claim_type: social_youtube
    claim_value: https://www.youtube.com/channel/UCa0uF7kyU0vLxKO5qx-ZHNg/videos?reload=9&app=desktop&view=0&sort=da&flow=grid&cbrd=1
    raw_value: https://www.youtube.com/channel/UCa0uF7kyU0vLxKO5qx-ZHNg/videos?reload=9&app=desktop&view=0&sort=da&flow=grid&cbrd=1
@ -600,6 +590,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:28.738156+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Cultuurhistorische Vereniging Zevenaar
--- a/data/nde/enriched/entries/0155_Q13636575.yaml
+++ b/data/nde/enriched/entries/0155_Q13636575.yaml
@ -963,18 +963,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:29.855125+00:00'
  source_archive: web/0155/streekmuseumtiel.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Flipje en Streekmuseum Tiel
-    source_url: https://streekmuseumtiel.nl/
-    retrieved_on: ''
-    xpath: /html/head/title
-    html_file: web/0155/streekmuseumtiel.nl/mirror/streekmuseumtiel.nl/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:29.854444+00:00'
  - claim_type: description_short
    claim_value: "DUIK IN DE\nHISTORIE \n\nIn het Flipje en Streekmuseum wordt de\
      \ historie van Tiel en de Betuwe getoond. Ook haar beroemdste inwoner - Flipje\
@ -1041,6 +1031,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:29.855011+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Flipje & Streekmuseum Tiel
--- a/data/nde/enriched/entries/0157_Q104033126.yaml
+++ b/data/nde/enriched/entries/0157_Q104033126.yaml
@ -510,18 +510,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:29.935972+00:00'
  source_archive: web/0157/gelderlandinbeeld.nl
-  claims_count: 3
+  claims_count: 2
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Gelderland in beeld
-    source_url: https://www.gelderlandinbeeld.nl/
-    retrieved_on: '2025-11-29T15:22:43.989143+00:00'
-    xpath: /html/head/title
-    html_file: web/0157/gelderlandinbeeld.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:29.935777+00:00'
  - claim_type: email
    claim_value: erfgoedcentrum@rozet.nl
    raw_value: erfgoedcentrum@rozet.nl
@ -542,6 +532,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:29.935958+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gelderland in Beeld
--- a/data/nde/enriched/entries/0158_Q2330735.yaml
+++ b/data/nde/enriched/entries/0158_Q2330735.yaml
@ -793,18 +793,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:30.034033+00:00'
  source_archive: web/0158/geldersarchief.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: http://www.geldersarchief.nl
-    retrieved_on: '2025-11-29T15:22:43.748847+00:00'
-    xpath: /html/head/title
-    html_file: web/0158/geldersarchief.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:30.032762+00:00'
  - claim_type: org_name
    claim_value: chat
    raw_value: chat
@ -881,6 +871,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:30.033839+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gelders Archief
--- a/data/nde/enriched/entries/0159_Q4688292.yaml
+++ b/data/nde/enriched/entries/0159_Q4688292.yaml
@ -709,18 +709,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:30.419385+00:00'
  source_archive: web/0159/geologischmuseum.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Gelders Geologisch Museum
-    source_url: https://geologischmuseum.nl/
-    retrieved_on: '2025-11-29T15:22:49.377757+00:00'
-    xpath: /html/head/title
-    html_file: web/0159/geologischmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:30.418790+00:00'
  - claim_type: org_name
    claim_value: Gelders Geologisch Museum
    raw_value: Gelders Geologisch Museum
@ -781,6 +771,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:30.419326+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gelders Geologisch Museum
--- a/data/nde/enriched/entries/0165_Q81181326.yaml
+++ b/data/nde/enriched/entries/0165_Q81181326.yaml
@ -496,18 +496,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:31.788139+00:00'
  source_archive: web/0165/nijkerk.eu
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Nijkerk
-    source_url: https://www.nijkerk.eu/gemeentearchief
-    retrieved_on: '2025-11-29T15:22:51.188307+00:00'
-    xpath: /html/head/title
-    html_file: web/0165/nijkerk.eu/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:31.787315+00:00'
  - claim_type: org_name
    claim_value: Toegankelijkheid
    raw_value: Toegankelijkheid
@ -548,6 +538,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:31.787782+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Nijkerk
--- a/data/nde/enriched/entries/0169_Q2332962.yaml
+++ b/data/nde/enriched/entries/0169_Q2332962.yaml
@ -673,18 +673,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:32.713519+00:00'
  source_archive: web/0169/belmontearboretum.nl
-  claims_count: 4
+  claims_count: 3
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Belmonte Arboretum
-    source_url: https://belmontearboretum.nl/
-    retrieved_on: '2025-11-29T15:26:05.199368+00:00'
-    xpath: /html/head/title
-    html_file: web/0169/belmontearboretum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:32.713034+00:00'
  - claim_type: org_name
    claim_value: Belmonte Arboretum
    raw_value: Belmonte Arboretum
@ -715,6 +705,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:32.713421+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Belmonte Arboretum
--- a/data/nde/enriched/entries/0170_Q2365901.yaml
+++ b/data/nde/enriched/entries/0170_Q2365901.yaml
@ -688,7 +688,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:33.192176+00:00'
  source_archive: web/0170/grenslandmuseum.nl
-  claims_count: 10
+  claims_count: 8
  claims:
  - claim_type: org_name
    claim_value: Stichting Grenslandmuseum Dinxperlo
@ -700,26 +700,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:33.191065+00:00'
-  - claim_type: org_name
-    claim_value: Previous
-    raw_value: Previous
-    source_url: https://www.grenslandmuseum.nl/
-    retrieved_on: '2025-11-29T15:26:21.418250+00:00'
-    xpath: /html/body/div[1]/div/div[1]/div/div[1]/a[1]/svg/title
-    html_file: web/0170/grenslandmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:33.191079+00:00'
-  - claim_type: org_name
-    claim_value: Next
-    raw_value: Next
-    source_url: https://www.grenslandmuseum.nl/
-    retrieved_on: '2025-11-29T15:26:21.418250+00:00'
-    xpath: /html/body/div[1]/div/div[1]/div/div[1]/a[2]/svg/title
-    html_file: web/0170/grenslandmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:33.191084+00:00'
  - claim_type: org_name
    claim_value: Right-open
    raw_value: Right-open
@ -790,6 +770,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:33.191917+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Grenslandmuseum
--- a/data/nde/enriched/entries/0172_Q98907725.yaml
+++ b/data/nde/enriched/entries/0172_Q98907725.yaml
@ -546,18 +546,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:33.713426+00:00'
  source_archive: web/0172/heemkundekringbergh.nl
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Heemkundekring Bergh
-    source_url: https://www.heemkundekringbergh.nl
-    retrieved_on: '2025-11-29T15:27:37.429075+00:00'
-    xpath: /html/head/title
-    html_file: web/0172/heemkundekringbergh.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:33.712712+00:00'
  - claim_type: description_short
    claim_value: Homepagina
    raw_value: Homepagina
@ -600,6 +590,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:33.713325+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Heemkundekring Bergh
--- a/data/nde/enriched/entries/0174_heiligenbeeldenmuseum_kranenburg.yaml
+++ b/data/nde/enriched/entries/0174_heiligenbeeldenmuseum_kranenburg.yaml
@ -225,18 +225,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:34.113320+00:00'
  source_archive: web/0174/heiligenbeeldenmuseum.nl
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Heiligenbeeldenmuseum Kranenburg
-    source_url: https://www.heiligenbeeldenmuseum.nl/
-    retrieved_on: '2025-11-29T15:26:10.471256+00:00'
-    xpath: /html/head/title
-    html_file: web/0174/heiligenbeeldenmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:34.112922+00:00'
  - claim_type: description_short
    claim_value: Heiligenbeeldenmuseum Kranenburg
    raw_value: Heiligenbeeldenmuseum Kranenburg
@ -277,6 +267,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:34.113278+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Het Heiligenbeeldenmuseum
--- a/data/nde/enriched/entries/0177_Q7476442.yaml
+++ b/data/nde/enriched/entries/0177_Q7476442.yaml
@ -826,7 +826,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:34.449363+00:00'
  source_archive: web/0177/historischmuseumede.nl
-  claims_count: 13
+  claims_count: 10
  claims:
  - claim_type: org_name
    claim_value: Historisch Museum Ede brengt verhalen van Ede tot leven
@ -848,16 +848,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:34.448156+00:00'
-  - claim_type: org_name
-    claim_value: Zoeken
-    raw_value: Zoeken
-    source_url: https://www.historischmuseumede.nl
-    retrieved_on: '2025-11-29T15:26:16.779276+00:00'
-    xpath: /html/body/div[1]/header/div[1]/div/div/div/div[2]/div/div/div/div[2]/div[2]/div/button/span[2]/span/svg/title
-    html_file: web/0177/historischmuseumede.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:34.448181+00:00'
  - claim_type: org_name
    claim_value: Uren
    raw_value: Uren
@ -940,26 +930,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: tel_link
    extraction_timestamp: '2025-12-01T10:44:34.448927+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fhistorischmuseumede.nl%2Fevents%2Fverwacht-verkerke-edese-wereldspeler-in-posters%2F
-    raw_value: https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fhistorischmuseumede.nl%2Fevents%2Fverwacht-verkerke-edese-wereldspeler-in-posters%2F
-    source_url: https://www.historischmuseumede.nl
-    retrieved_on: '2025-11-29T15:26:16.779276+00:00'
-    xpath: /html/body/div[1]/main/div/div/div/div/article/div/div/div[6]/div/div/div/div/div[1]/div/div/article/div[2]/ul/li[2]/ul/li[1]/a
-    html_file: web/0177/historischmuseumede.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:34.449077+00:00'
-  - claim_type: social_twitter
-    claim_value: https://twitter.com/share?url=https%3A%2F%2Fhistorischmuseumede.nl%2Fevents%2Fverwacht-verkerke-edese-wereldspeler-in-posters%2F
-    raw_value: https://twitter.com/share?url=https%3A%2F%2Fhistorischmuseumede.nl%2Fevents%2Fverwacht-verkerke-edese-wereldspeler-in-posters%2F
-    source_url: https://www.historischmuseumede.nl
-    retrieved_on: '2025-11-29T15:26:16.779276+00:00'
-    xpath: /html/body/div[1]/main/div/div/div/div/article/div/div/div[6]/div/div/div/div/div[1]/div/div/article/div[2]/ul/li[2]/ul/li[2]/a
-    html_file: web/0177/historischmuseumede.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:34.449084+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historisch Museum Ede
--- a/data/nde/enriched/entries/0178_Q98904482.yaml
+++ b/data/nde/enriched/entries/0178_Q98904482.yaml
@ -295,18 +295,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:34.584225+00:00'
  source_archive: web/0178/historischmuseumhedel.nl
-  claims_count: 4
+  claims_count: 3
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://www.historischmuseumhedel.nl/
-    retrieved_on: '2025-11-29T15:26:19.658845+00:00'
-    xpath: /html/head/title
-    html_file: web/0178/historischmuseumhedel.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:34.583694+00:00'
  - claim_type: org_name
    claim_value: Historisch Museum Hedel
    raw_value: Historisch Museum Hedel
@ -337,6 +327,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:34.584143+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Hedel's Historie
--- a/data/nde/enriched/entries/0184_Q38677497.yaml
+++ b/data/nde/enriched/entries/0184_Q38677497.yaml
@ -939,7 +939,7 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:36.137017+00:00'
  source_archive: web/0184/gemeentearchief.ede.nl
-  claims_count: 7
+  claims_count: 6
  claims:
  - claim_type: org_name
    claim_value: Gemeentearchief Ede
@ -951,16 +951,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:36.136505+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer/sharer.php?u=https://gemeentearchief.ede.nl/
-    raw_value: https://www.facebook.com/sharer/sharer.php?u=https://gemeentearchief.ede.nl/
-    source_url: https://gemeentearchief.ede.nl
-    retrieved_on: '2025-11-29T15:26:47.211861+00:00'
-    xpath: /html/body/div/div/main/section/div[6]/div/div/ul/li[1]/a
-    html_file: web/0184/gemeentearchief.ede.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:36.136893+00:00'
  - claim_type: social_linkedin
    claim_value: https://www.linkedin.com/sharing/share-offsite/?url=https://gemeentearchief.ede.nl/
    raw_value: https://www.linkedin.com/sharing/share-offsite/?url=https://gemeentearchief.ede.nl/
@ -1011,6 +1001,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:36.136923+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeente Ede
--- a/data/nde/enriched/entries/0186_Q98894809.yaml
+++ b/data/nde/enriched/entries/0186_Q98894809.yaml
@ -503,18 +503,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:36.794780+00:00'
  source_archive: web/0186/hkwestervoort.nl
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: HOME
-    raw_value: HOME - Historische Kring Westervoort
-    source_url: https://www.hkwestervoort.nl
-    retrieved_on: '2025-11-29T15:27:14.285337+00:00'
-    xpath: /html/head/title
-    html_file: web/0186/hkwestervoort.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:36.792802+00:00'
  - claim_type: description_short
    claim_value: Historische Kring Westervoort
    raw_value: Historische Kring Westervoort
@ -555,6 +545,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:36.794479+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historische Kring Westervoort
--- a/data/nde/enriched/entries/0201_Q98895215.yaml
+++ b/data/nde/enriched/entries/0201_Q98895215.yaml
@ -632,18 +632,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:40.581965+00:00'
  source_archive: web/0201/historischeverenigingvoorst.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: https://www.historischeverenigingvoorst.nl
-    retrieved_on: '2025-11-29T15:29:57.119726+00:00'
-    xpath: /html/head/title
-    html_file: web/0201/historischeverenigingvoorst.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:40.580692+00:00'
  - claim_type: org_name
    claim_value: Datum
    raw_value: Datum
@ -714,6 +704,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:40.581750+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Historische Vereniging Voorst
--- a/data/nde/enriched/entries/0202_Q61930724.yaml
+++ b/data/nde/enriched/entries/0202_Q61930724.yaml
@ -928,18 +928,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:40.670247+00:00'
  source_archive: web/0202/bronbeek.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Bronbeek
-    source_url: https://www.bronbeek.nl/
-    retrieved_on: '2025-11-29T15:29:53.013757+00:00'
-    xpath: /html/head/title
-    html_file: web/0202/bronbeek.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:40.669788+00:00'
  - claim_type: description_short
    claim_value: Bronbeek is een museum en hét kenniscentrum van het koloniaal-militair
      verleden van het Koninkrijk der Nederlanden. Het bevindt zich op een cultuurhistorisch
@ -996,6 +986,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:40.670137+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Koninklijk Tehuis voor Oud-Militairen en Museum Bronbeek
--- a/data/nde/enriched/entries/0203_stichting_korpora.yaml
+++ b/data/nde/enriched/entries/0203_stichting_korpora.yaml
@ -399,18 +399,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:41.114748+00:00'
  source_archive: web/0203/korpora.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Korpora
-    source_url: https://www.korpora.nl/
-    retrieved_on: '2025-11-29T15:32:28.709223+00:00'
-    xpath: /html/head/title
-    html_file: web/0203/korpora.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:41.113200+00:00'
  - claim_type: org_name
    claim_value: Korpora
    raw_value: Korpora
@ -461,6 +451,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:41.114337+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Korpora
--- a/data/nde/enriched/entries/0213_Q54957003.yaml
+++ b/data/nde/enriched/entries/0213_Q54957003.yaml
@ -894,7 +894,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:43.665080+00:00'
  source_archive: web/0213/vantlindenhoutmuseum.nl
-  claims_count: 10
+  claims_count: 8
  claims:
  - claim_type: org_name
    claim_value: Museum Kinderdorp Neerbosch Nijmegen
@ -920,16 +920,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: meta_description
    extraction_timestamp: '2025-12-01T10:44:43.664098+00:00'
-  - claim_type: org_name
-    claim_value: museumkinderdorpneerbosch.nl
-    raw_value: museumkinderdorpneerbosch.nl
-    source_url: http://www.vantlindenhoutmuseum.nl
-    retrieved_on: '2025-11-29T15:31:25.473939+00:00'
-    xpath: /html/head/meta[10]
-    html_file: web/0213/vantlindenhoutmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: og_site_name
-    extraction_timestamp: '2025-12-01T10:44:43.664302+00:00'
  - claim_type: email
    claim_value: info@museumkinderdorpneerbosch.nl
    raw_value: info@museumkinderdorpneerbosch.nl
@ -990,16 +980,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:43.664714+00:00'
-  - claim_type: org_name
-    claim_value: NIEUWS
-    raw_value: NIEUWS
-    source_url: http://www.vantlindenhoutmuseum.nl
-    retrieved_on: '2025-11-29T15:31:25.473939+00:00'
-    xpath: /html/body/div/div/div/div/div[2]/div/div/section[1]/div/div/div/div/div/div[1]/div/h1
-    html_file: web/0213/vantlindenhoutmuseum.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:43.664765+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Kinderdorp Neerbosch
--- a/data/nde/enriched/entries/0219_Q109382770.yaml
+++ b/data/nde/enriched/entries/0219_Q109382770.yaml
@ -532,18 +532,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:45.516054+00:00'
  source_archive: web/0219/museumoene.nl
-  claims_count: 3
+  claims_count: 2
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Cultuur Historisch Museum Oene
-    source_url: https://museumoene.nl
-    retrieved_on: '2025-11-29T15:33:01.789691+00:00'
-    xpath: /html/head/title
-    html_file: web/0219/museumoene.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:45.515544+00:00'
  - claim_type: description_short
    claim_value: Cultuur Historisch Museum Oene
    raw_value: Cultuur Historisch Museum Oene
@ -564,6 +554,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:45.515976+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Cultuur Historisch Museum Oene
--- a/data/nde/enriched/entries/0220_Q98961921.yaml
+++ b/data/nde/enriched/entries/0220_Q98961921.yaml
@ -740,7 +740,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:45.976892+00:00'
  source_archive: web/0220/sjoelelburg.nl
-  claims_count: 5
+  claims_count: 2
  claims:
  - claim_type: org_name
    claim_value: Museum Sjoel Elburg
@ -780,124 +780,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: og_description
    extraction_timestamp: '2025-12-01T10:44:45.976067+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer/sharer.php?u=https://sjoelelburg.nl/&t=Het
-      Museum
-    raw_value: https://www.facebook.com/sharer/sharer.php?u=https://sjoelelburg.nl/&t=Het
-      Museum
-    source_url: https://sjoelelburg.nl/
-    retrieved_on: '2025-11-29T15:36:05.747990+00:00'
-    xpath: /html/body/div/div[5]/div/div/div/div/div[3]/ul/li[2]/a
-    html_file: web/0220/sjoelelburg.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:45.976626+00:00'
-  - claim_type: social_twitter
-    claim_value: https://twitter.com/intent/tweet?source=https://sjoelelburg.nl/&text=Het
-      Museum:https://sjoelelburg.nl/
-    raw_value: https://twitter.com/intent/tweet?source=https://sjoelelburg.nl/&text=Het
-      Museum:https://sjoelelburg.nl/
-    source_url: https://sjoelelburg.nl/
-    retrieved_on: '2025-11-29T15:36:05.747990+00:00'
-    xpath: /html/body/div/div[5]/div/div/div/div/div[3]/ul/li[3]/a
-    html_file: web/0220/sjoelelburg.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:45.976635+00:00'
-  - claim_type: social_linkedin
-    claim_value: 'http://www.linkedin.com/shareArticle?mini=true&url=https://sjoelelburg.nl/&title=Het
-      Museum&summary=Steun het museum Openingstijden en prijzen Museum Sjoel ElburgMuseum
-      Sjoel Elburg is... een verhalenmuseum over het (on)gewone dagelijks leven van
-      joodse families die vanaf 1700 in Elburg hebben gewoond. Museum Sjoel Elburg
-      biedt... een historisch perspectief voor een actueel thema: integratie en verdraagzaamheid.
-      Museum Sjoel Elburg presenteert... de joodse geschiedenis op een dynamische,
-      onorthodoxe, boeiende en eigenzinnige wijze en laat daarmee een eigen museaal
-      geluid horen. De inrichting De inrichting van Museum Sjoel Elburg is tot stand
-      gekomen met medewerking van DJO Ontwerpers Den Haag en Cultuurproject Apeldoorn.
-      Inrichting museum De tentoonstellingVan 11 juli tot en met 29 november 2025
-      de serie ‘Chassidische legenden’ te zien van de Groninger kunstenaar H.N. Werkman
-      De tentoonstelling Educatie Een bezoek aan Museum Sjoel Elburg is een unieke
-      ervaring. Nergens in Nederland is de geschiedenis van de joden in de mediene
-      – de provincie – zo mooi uitgewerkt als in dit museum. EDUCATIEJoden in Elburg
-      Namenlijst Ter herinnering: alle namen en gegevens van in Elburg geboren slachtoffers.
-      JODEN IN ELBURG 30 nov Sophie Northeimer (1899-1973) 16 mei Josef Steinhauer
-      16 mei Gerda Steinhauer 14 mei Jozeph de Lange 11 mei Jozeph Beem 08 mrt Barend
-      de Hond 08 mrt Klaartje de Hond – de laatste brief HET LAATSTE NIEUWS 30 okt
-      Zoektocht naar onderduikgevers van Joods echtpaar Gans-Koopman Het Joodse echtpaar
-      Gesina Gans-Koopman en Eli Gans uit Amsterdam duikt in 1944 in Doornspijk onder.
-      Gesina heeft een vals persoonsbewijs op naam van Gesina Lees meer 26 okt Sjoellezing
-      20 november 2025 Op uitnodiging van de Vrienden van Museum Sjoel Elburg verzorgt
-      drs. Cor Hoogerwerf op donderdag 20 november 2025 in de Ichthuskerk te Elburg
-      de Sjoellezing Lees meer 10 okt Sjoel ontvangt ruim 1000 euro via Rabo ClubSupport
-      Museum Sjoel Elburg deed dit jaar weer mee met de actie Rabo ClubSupport en
-      dat was niet zonder resultaat. Penningmeester en bestuurslid van Museum Sjoel
-      Lees meer 08 okt Najaarscursus 2025: ‘Joodse wijsheid en filosofie’ Wat is wijsheid?
-      Hoe leef je een goed en betekenisvol leven? Eeuwenlang zochten Joodse denkers
-      naar antwoorden op deze vragen. In de najaarscursus van 2025 Lees meer 28 aug
-      Vreugde in duistere tijden Van een vriend kreeg de Groninger kunstenaar en drukker
-      Hendrik Nicolaas Werkman het boekje ‘Die Legende des Baalsjems’ van de Joodse
-      godsdienstfilosoof Martin Buber te Lees meer 26 jul Oude Joodse legenden als
-      vorm van verzet Wat moet je in het heden met vertellingen van hemelwandelingen,
-      vliegende paarden en de wederopstanding van een Joodse bruid? De Groninger kunstenaar
-      H.N. Werkman zag Lees meer 17 jul In memoriam Theo van Ledden (1945-2025) Met
-      droefenis delen wij het bericht van het overlijden van Theo van Ledden. Theo
-      was oud-voorzitter van het bestuur van Museum Sjoel Elburg. Hij blijft Lees
-      meer 11 jul Chassidische legenden in de sjoel Tot en met 29 november biedt Museum
-      Sjoel Elburg de tentoonstelling ‘H.N. Werkman. Chassidische legenden en de kunst
-      van het verzet’. De opening werd 10 Lees meer Tentoonstellingen Verwacht 06
-      dec, 2025 Mag Saar er zijn? Openingstijden en prijzen MUSEUM SJOEL ELBURG IS
-      WEER OPEN!Welkom! Museum Sjoel Elburg is weer open, zij het met nieuwe coronaregels
-      van doen en laten en onder de […]&source=https://sjoelelburg.nl/'
-    raw_value: 'http://www.linkedin.com/shareArticle?mini=true&url=https://sjoelelburg.nl/&title=Het
-      Museum&summary=Steun het museum Openingstijden en prijzen Museum Sjoel ElburgMuseum
-      Sjoel Elburg is... een verhalenmuseum over het (on)gewone dagelijks leven van
-      joodse families die vanaf 1700 in Elburg hebben gewoond. Museum Sjoel Elburg
-      biedt... een historisch perspectief voor een actueel thema: integratie en verdraagzaamheid.
-      Museum Sjoel Elburg presenteert... de joodse geschiedenis op een dynamische,
-      onorthodoxe, boeiende en eigenzinnige wijze en laat daarmee een eigen museaal
-      geluid horen. De inrichting De inrichting van Museum Sjoel Elburg is tot stand
-      gekomen met medewerking van DJO Ontwerpers Den Haag en Cultuurproject Apeldoorn.
-      Inrichting museum De tentoonstellingVan 11 juli tot en met 29 november 2025
-      de serie ‘Chassidische legenden’ te zien van de Groninger kunstenaar H.N. Werkman
-      De tentoonstelling Educatie Een bezoek aan Museum Sjoel Elburg is een unieke
-      ervaring. Nergens in Nederland is de geschiedenis van de joden in de mediene
-      – de provincie – zo mooi uitgewerkt als in dit museum. EDUCATIEJoden in Elburg
-      Namenlijst Ter herinnering: alle namen en gegevens van in Elburg geboren slachtoffers.
-      JODEN IN ELBURG 30 nov Sophie Northeimer (1899-1973) 16 mei Josef Steinhauer
-      16 mei Gerda Steinhauer 14 mei Jozeph de Lange 11 mei Jozeph Beem 08 mrt Barend
-      de Hond 08 mrt Klaartje de Hond – de laatste brief HET LAATSTE NIEUWS 30 okt
-      Zoektocht naar onderduikgevers van Joods echtpaar Gans-Koopman Het Joodse echtpaar
-      Gesina Gans-Koopman en Eli Gans uit Amsterdam duikt in 1944 in Doornspijk onder.
-      Gesina heeft een vals persoonsbewijs op naam van Gesina Lees meer 26 okt Sjoellezing
-      20 november 2025 Op uitnodiging van de Vrienden van Museum Sjoel Elburg verzorgt
-      drs. Cor Hoogerwerf op donderdag 20 november 2025 in de Ichthuskerk te Elburg
-      de Sjoellezing Lees meer 10 okt Sjoel ontvangt ruim 1000 euro via Rabo ClubSupport
-      Museum Sjoel Elburg deed dit jaar weer mee met de actie Rabo ClubSupport en
-      dat was niet zonder resultaat. Penningmeester en bestuurslid van Museum Sjoel
-      Lees meer 08 okt Najaarscursus 2025: ‘Joodse wijsheid en filosofie’ Wat is wijsheid?
-      Hoe leef je een goed en betekenisvol leven? Eeuwenlang zochten Joodse denkers
-      naar antwoorden op deze vragen. In de najaarscursus van 2025 Lees meer 28 aug
-      Vreugde in duistere tijden Van een vriend kreeg de Groninger kunstenaar en drukker
-      Hendrik Nicolaas Werkman het boekje ‘Die Legende des Baalsjems’ van de Joodse
-      godsdienstfilosoof Martin Buber te Lees meer 26 jul Oude Joodse legenden als
-      vorm van verzet Wat moet je in het heden met vertellingen van hemelwandelingen,
-      vliegende paarden en de wederopstanding van een Joodse bruid? De Groninger kunstenaar
-      H.N. Werkman zag Lees meer 17 jul In memoriam Theo van Ledden (1945-2025) Met
-      droefenis delen wij het bericht van het overlijden van Theo van Ledden. Theo
-      was oud-voorzitter van het bestuur van Museum Sjoel Elburg. Hij blijft Lees
-      meer 11 jul Chassidische legenden in de sjoel Tot en met 29 november biedt Museum
-      Sjoel Elburg de tentoonstelling ‘H.N. Werkman. Chassidische legenden en de kunst
-      van het verzet’. De opening werd 10 Lees meer Tentoonstellingen Verwacht 06
-      dec, 2025 Mag Saar er zijn? Openingstijden en prijzen MUSEUM SJOEL ELBURG IS
-      WEER OPEN!Welkom! Museum Sjoel Elburg is weer open, zij het met nieuwe coronaregels
-      van doen en laten en onder de […]&source=https://sjoelelburg.nl/'
-    source_url: https://sjoelelburg.nl/
-    retrieved_on: '2025-11-29T15:36:05.747990+00:00'
-    xpath: /html/body/div/div[5]/div/div/div/div/div[3]/ul/li[5]/a
-    html_file: web/0220/sjoelelburg.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:45.976653+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Sjoel Elburg
--- a/data/nde/enriched/entries/0225_Q98908556.yaml
+++ b/data/nde/enriched/entries/0225_Q98908556.yaml
@ -1000,18 +1000,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:47.390334+00:00'
  source_archive: web/0225/slotloevestein.nl
-  claims_count: 7
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Slot Loevestein
-    raw_value: Slot Loevestein - Slot Loevestein - Rijksmuseum
-    source_url: http://www.slotloevestein.nl/
-    retrieved_on: '2025-11-29T15:36:51.543964+00:00'
-    xpath: /html/head/title
-    html_file: web/0225/slotloevestein.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:47.388969+00:00'
  - claim_type: description_short
    claim_value: 'Rijksmuseum Slot Loevestein - UNESCO Werelderfgoed Nieuwe Hollandse
      Waterlinie - Beroemdste gevangene: Hugo de Groot. Ontsnapt in boekenkist.'
@ -1024,16 +1014,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: meta_description
    extraction_timestamp: '2025-12-01T10:44:47.389211+00:00'
-  - claim_type: org_name
-    claim_value: Slot Loevestein - Rijksmuseum
-    raw_value: Slot Loevestein - Rijksmuseum
-    source_url: http://www.slotloevestein.nl/
-    retrieved_on: '2025-11-29T15:36:51.543964+00:00'
-    xpath: /html/head/meta[10]
-    html_file: web/0225/slotloevestein.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: og_site_name
-    extraction_timestamp: '2025-12-01T10:44:47.389563+00:00'
  - claim_type: email
    claim_value: info@slotloevestein.nl
    raw_value: info@slotloevestein.nl
@ -1074,6 +1054,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:47.390140+00:00'
+  removed_invalid_claims:
+  - removed_count: 2
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Rijksmuseum Slot Loevestein
--- a/data/nde/enriched/entries/0226_Q98893885.yaml
+++ b/data/nde/enriched/entries/0226_Q98893885.yaml
@ -387,18 +387,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:47.493414+00:00'
  source_archive: web/0226/museumveluwezoom.nl
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Museum Veluwezoom
-    source_url: https://www.museumveluwezoom.nl/
-    retrieved_on: '2025-11-29T15:34:48.112339+00:00'
-    xpath: /html/head/title
-    html_file: web/0226/museumveluwezoom.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:47.492523+00:00'
  - claim_type: description_short
    claim_value: Museum Veluwezoom, gevestigd in Kasteel Doorwerth, biedt tentoonstellingen
      over de kunstenaarskolonie in Oosterbeek en de Veluwezoom.
@ -441,6 +431,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:47.493260+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum Veluwezoom
--- a/data/nde/enriched/entries/0230_Q18774274.yaml
+++ b/data/nde/enriched/entries/0230_Q18774274.yaml
@ -609,7 +609,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:48.857637+00:00'
  source_archive: web/0230/mariahoeveputten.nl
-  claims_count: 14
+  claims_count: 11
  claims:
  - claim_type: org_name
    claim_value: Mariahoeve Putten
@ -621,36 +621,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:48.857013+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://mariahoeveputten.nl/
-    retrieved_on: '2025-11-29T15:37:22.983423+00:00'
-    xpath: /html/body/footer/div[1]/div/div[1]/div[5]/ul/li[1]/a/svg/title
-    html_file: web/0230/mariahoeveputten.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:48.857027+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://mariahoeveputten.nl/
-    retrieved_on: '2025-11-29T15:37:22.983423+00:00'
-    xpath: /html/body/footer/div[1]/div/div[1]/div[5]/ul/li[2]/a/svg/title
-    html_file: web/0230/mariahoeveputten.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:48.857033+00:00'
-  - claim_type: org_name
-    claim_value: YouTube
-    raw_value: YouTube
-    source_url: https://mariahoeveputten.nl/
-    retrieved_on: '2025-11-29T15:37:22.983423+00:00'
-    xpath: /html/body/footer/div[1]/div/div[1]/div[5]/ul/li[3]/a/svg/title
-    html_file: web/0230/mariahoeveputten.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:48.857037+00:00'
  - claim_type: org_name
    claim_value: Museumboerderij De Mariahoeve
    raw_value: Museumboerderij De Mariahoeve
@ -751,6 +721,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:48.857555+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museumboerderij Mariahoeve
--- a/data/nde/enriched/entries/0234_Q2710899.yaml
+++ b/data/nde/enriched/entries/0234_Q2710899.yaml
@ -851,18 +851,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:50.618049+00:00'
  source_archive: web/0234/nationaalonderduikmuseum.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Nationaal onderduikmuseum
-    source_url: https://nationaalonderduikmuseum.nl
-    retrieved_on: '2025-11-29T15:40:23.434916+00:00'
-    xpath: /html/head/title
-    html_file: web/0234/nationaalonderduikmuseum.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:50.616994+00:00'
  - claim_type: org_name
    claim_value: Nationaal onderduikmuseum -
    raw_value: Nationaal onderduikmuseum -
@ -943,6 +933,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:50.617944+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Nationaal Onderduikmuseum
--- a/data/nde/enriched/entries/0245_Q98907726.yaml
+++ b/data/nde/enriched/entries/0245_Q98907726.yaml
@ -477,7 +477,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:53.689231+00:00'
  source_archive: web/0245/oudheidkundigeverenigingwehl.nl
-  claims_count: 2
+  claims_count: 1
  claims:
  - claim_type: org_name
    claim_value: Oudheidkundige vereniging Wehl
@ -489,16 +489,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:53.688202+00:00'
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: http://www.oudheidkundigeverenigingwehl.nl
-    retrieved_on: '2025-11-29T15:39:17.440024+00:00'
-    xpath: /html/body/div/div/div/div/main/article/header/h1
-    html_file: web/0245/oudheidkundigeverenigingwehl.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:53.689023+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Oudheidkundige Vereniging Wehl
--- a/data/nde/enriched/entries/0246_Q98895220.yaml
+++ b/data/nde/enriched/entries/0246_Q98895220.yaml
@ -321,7 +321,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:54.060526+00:00'
  source_archive: web/0246/zuwent.nl
-  claims_count: 2
+  claims_count: 1
  claims:
  - claim_type: org_name
    claim_value: Oudheidkundige Vereniging Zuwent
@ -333,16 +333,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:44:54.059903+00:00'
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: http://zuwent.nl
-    retrieved_on: '2025-11-29T15:39:48.774087+00:00'
-    xpath: /html/body/div/div/div/div/div/main/div[1]/h1
-    html_file: web/0246/zuwent.nl/pages/index.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T10:44:54.060459+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Oudheidkundige Vereniging Zuwent
--- a/data/nde/enriched/entries/0251_Q26203717.yaml
+++ b/data/nde/enriched/entries/0251_Q26203717.yaml
@ -848,22 +848,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:55.005764+00:00'
  source_archive: web/0251/regionaalarchiefrivierenland.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
-      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
-      Neder-Betuwe, Tiel en Zaltbommel en over polders en waterschappen in Rivierenland.
-    raw_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
-      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
-      Neder-Betuwe, Tiel en Zaltbommel en over polders en waterschappen in Rivierenland.
-    source_url: https://regionaalarchiefrivierenland.nl/home
-    retrieved_on: '2025-11-29T15:39:50.244225+00:00'
-    xpath: /html/head/title
-    html_file: web/0251/regionaalarchiefrivierenland.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:55.004643+00:00'
  - claim_type: description_short
    claim_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
@ -918,6 +904,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:55.005600+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Regionaal Archief Rivierenland
--- a/data/nde/enriched/entries/0252_Q81181406.yaml
+++ b/data/nde/enriched/entries/0252_Q81181406.yaml
@ -553,18 +553,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:55.136545+00:00'
  source_archive: web/0252/erfgoedcentrumzutphen.nl
-  claims_count: 12
+  claims_count: 11
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Erfgoedcentrum Zutphen
-    source_url: https://erfgoedcentrumzutphen.nl/
-    retrieved_on: '2025-11-29T15:39:50.527456+00:00'
-    xpath: /html/head/title
-    html_file: web/0252/erfgoedcentrumzutphen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:55.135283+00:00'
  - claim_type: description_short
    claim_value: 'Het Erfgoedcentrum Zutphen: historisch hart van de regio! Eén plek
      voor onze vier erfgoedpartners: Archeologie, Monumentenzorg, Musea Zutphen en
@ -679,6 +669,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:55.136478+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Regionaal Archief Zutphen | Erfgoedcentrum Zutphen
--- a/data/nde/enriched/entries/0258_Q56459713.yaml
+++ b/data/nde/enriched/entries/0258_Q56459713.yaml
@ -872,18 +872,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:56.930660+00:00'
  source_archive: web/0258/stadsmuseum-harderwijk.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Stadsmuseum Harderwijk
-    source_url: https://www.stadsmuseum-harderwijk.nl/
-    retrieved_on: '2025-11-29T15:41:05.031608+00:00'
-    xpath: /html/head/title
-    html_file: web/0258/stadsmuseum-harderwijk.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:56.930073+00:00'
  - claim_type: org_name
    claim_value: Stadsmuseum Harderwijk
    raw_value: Stadsmuseum Harderwijk
@ -954,6 +944,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:44:56.930575+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stadsmuseum Harderwijk
--- a/data/nde/enriched/entries/0262_Q110995923.yaml
+++ b/data/nde/enriched/entries/0262_Q110995923.yaml
@ -500,7 +500,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:57.915376+00:00'
  source_archive: web/0262/buurderijdelagehof.nl
-  claims_count: 7
+  claims_count: 6
  claims:
  - claim_type: org_name
    claim_value: Buurderij De Lage Hof |
@ -562,16 +562,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:57.915141+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fbuurderijdelagehof.nl%2F
-    raw_value: https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fbuurderijdelagehof.nl%2F
-    source_url: https://buurderijdelagehof.nl/
-    retrieved_on: '2025-11-29T15:40:44.887084+00:00'
-    xpath: /html/body/div[1]/div/footer/div[1]/div/div[2]/div/div/div/div/div[1]/div[1]/div/div/div/div[3]/a
-    html_file: web/0262/buurderijdelagehof.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:44:57.915168+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Buurderij De Lage Hof
--- a/data/nde/enriched/entries/0263_Q98904476.yaml
+++ b/data/nde/enriched/entries/0263_Q98904476.yaml
@ -444,18 +444,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:44:58.361382+00:00'
  source_archive: web/0263/erfgoedlov.org
-  claims_count: 5
+  claims_count: 4
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Stichting Erfgoed Meubelfabriek L.O.V.
-    source_url: https://erfgoedlov.org/
-    retrieved_on: '2025-11-29T15:42:06.973774+00:00'
-    xpath: /html/head/title
-    html_file: web/0263/erfgoedlov.org/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:44:58.360020+00:00'
  - claim_type: description_short
    claim_value: Labor Omnia Vincit (Arbeid overwint alles)  was de idealistische
      strijdkreet van de in 1910 te Oosterbeek door Gerrit Pelt opgerichte meubelfabriek.
@ -504,6 +494,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:44:58.361105+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Stichting Erfgoed Meubelfabriek L.O.V
--- a/data/nde/enriched/entries/0273_streekarchief_bommelerwaard.yaml
+++ b/data/nde/enriched/entries/0273_streekarchief_bommelerwaard.yaml
@ -268,22 +268,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:01.077118+00:00'
  source_archive: web/0273/regionaalarchiefrivierenland.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
-      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
-      Neder-Betuwe, Tiel en Zaltbommel en over polders en waterschappen in Rivierenland.
-    raw_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
-      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
-      Neder-Betuwe, Tiel en Zaltbommel en over polders en waterschappen in Rivierenland.
-    source_url: https://regionaalarchiefrivierenland.nl/
-    retrieved_on: '2025-11-29T15:44:06.761754+00:00'
-    xpath: /html/head/title
-    html_file: web/0273/regionaalarchiefrivierenland.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:01.076512+00:00'
  - claim_type: description_short
    claim_value: Het RAR verzamelt en beheert archieven, afbeeldingen, kranten, boeken
      en documentatie over de gemeenten Buren, Culemborg, West Betuwe, Maasdriel,
@ -338,6 +324,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:01.077015+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Streekarchief Bommelwaard
--- a/data/nde/enriched/entries/0276_Q111190981.yaml
+++ b/data/nde/enriched/entries/0276_Q111190981.yaml
@ -415,18 +415,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:02.280716+00:00'
  source_archive: web/0276/noordveluwsarchief.nl
-  claims_count: 8
+  claims_count: 7
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - NoVA
-    source_url: https://noordveluwsarchief.nl/
-    retrieved_on: '2025-11-29T15:47:48.936473+00:00'
-    xpath: /html/head/title
-    html_file: web/0276/noordveluwsarchief.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:02.278739+00:00'
  - claim_type: description_short
    claim_value: Het noordveluws archief geeft toegang tot de geschiedenis van acht
      gemeenten op de Veluwe.
@ -499,6 +489,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:02.280407+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Streekarchivariaat Noordwest-Veluwe
--- a/data/nde/enriched/entries/0280_Q56459657.yaml
+++ b/data/nde/enriched/entries/0280_Q56459657.yaml
@ -638,18 +638,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:03.236578+00:00'
  source_archive: web/0280/hagedoornsplaatse.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Veluws Museum Hagedoorns Plaatse
-    source_url: http://www.hagedoornsplaatse.nl
-    retrieved_on: '2025-11-29T15:46:05.283440+00:00'
-    xpath: /html/head/title
-    html_file: web/0280/hagedoornsplaatse.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:03.234944+00:00'
  - claim_type: description_short
    claim_value: 'Water, historie en de Veluwe: samen komen zij tot leven bij Veluws
      Museum Hagedoorns Plaatse Nieuw dit seizoen! De gloednieuwe tentoonstelling
@ -740,6 +730,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:45:03.236230+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Veluws Museum Hagedoorns Plaatse
--- a/data/nde/enriched/entries/0283_vereniging_oudheidkunde_lichtenvoorde.yaml
+++ b/data/nde/enriched/entries/0283_vereniging_oudheidkunde_lichtenvoorde.yaml
@ -255,7 +255,7 @@ custodian_name:
 web_claims:
  extraction_timestamp: '2025-12-01T12:25:22.374849+00:00'
  source_archive: web/0283/zuwent.nl
-  claims_count: 2
+  claims_count: 1
  claims:
  - claim_type: org_name
    claim_value: Oudheidkundige Vereniging Zuwent
@ -267,13 +267,11 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T12:25:22.374268+00:00'
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home
-    source_url: http://www.zuwent.nl/
-    retrieved_on: ''
-    xpath: /html/body/div/div/div/div/div/main/div[1]/h1
-    html_file: web/0283/zuwent.nl/rendered.html
-    xpath_match_score: 0.9
-    extraction_method: h1_tag
-    extraction_timestamp: '2025-12-01T12:25:22.374780+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
--- a/data/nde/enriched/entries/0285_Q2470853.yaml
+++ b/data/nde/enriched/entries/0285_Q2470853.yaml
@ -1120,7 +1120,7 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:04.150070+00:00'
  source_archive: web/0285/bergendal.wereldmuseum.nl
-  claims_count: 12
+  claims_count: 9
  claims:
  - claim_type: org_name
    claim_value: 'Wereldmuseum Berg en Dal | Het Archief: 2014'
@ -1204,36 +1204,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:04.149232+00:00'
-  - claim_type: social_linkedin
-    claim_value: https://www.linkedin.com/shareArticle?mini=true&url=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&title=Het%20Archief%3A%202014%20-%202023&source=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&summary=Het%20Archief%3A%202014%20-%202023
-    raw_value: https://www.linkedin.com/shareArticle?mini=true&url=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&title=Het%20Archief%3A%202014%20-%202023&source=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&summary=Het%20Archief%3A%202014%20-%202023
-    source_url: https://bergendal.wereldmuseum.nl/nl
-    retrieved_on: '2025-11-29T15:47:20.084264+00:00'
-    xpath: /html/body/div[2]/div[2]/main/div[3]/div/section/div/div/div/div/div[2]/a[1]
-    html_file: web/0285/bergendal.wereldmuseum.nl/pages/nl.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:45:04.149438+00:00'
-  - claim_type: social_twitter
-    claim_value: https://twitter.com/intent/tweet?url=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&text=Het%20Archief%3A%202014%20-%202023&via=afrikamuseum&hashtags=afrikamuseum
-    raw_value: https://twitter.com/intent/tweet?url=https%3A//bergendal.wereldmuseum.nl/nl/node/4177&text=Het%20Archief%3A%202014%20-%202023&via=afrikamuseum&hashtags=afrikamuseum
-    source_url: https://bergendal.wereldmuseum.nl/nl
-    retrieved_on: '2025-11-29T15:47:20.084264+00:00'
-    xpath: /html/body/div[2]/div[2]/main/div[3]/div/section/div/div/div/div/div[2]/a[2]
-    html_file: web/0285/bergendal.wereldmuseum.nl/pages/nl.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:45:04.149462+00:00'
-  - claim_type: social_facebook
-    claim_value: https://www.facebook.com/sharer.php?u=https%3A//bergendal.wereldmuseum.nl/nl/node/4177
-    raw_value: https://www.facebook.com/sharer.php?u=https%3A//bergendal.wereldmuseum.nl/nl/node/4177
-    source_url: https://bergendal.wereldmuseum.nl/nl
-    retrieved_on: '2025-11-29T15:47:20.084264+00:00'
-    xpath: /html/body/div[2]/div[2]/main/div[3]/div/section/div/div/div/div/div[2]/a[3]
-    html_file: web/0285/bergendal.wereldmuseum.nl/pages/nl.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: social_link
-    extraction_timestamp: '2025-12-01T10:45:04.149468+00:00'
  - claim_type: org_name
    claim_value: 'Het Archief: 2014 - 2023'
    raw_value: 'Het Archief: 2014 - 2023'
@ -1244,6 +1214,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:45:04.149600+00:00'
+  removed_invalid_claims:
+  - removed_count: 3
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Wereldmuseum Berg en Dal
--- a/data/nde/enriched/entries/0286_Q484899.yaml
+++ b/data/nde/enriched/entries/0286_Q484899.yaml
@ -847,18 +847,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:04.559349+00:00'
  source_archive: web/0286/velorama.nl
-  claims_count: 7
+  claims_count: 6
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Nationaal Fietsmuseum Velorama
-    source_url: https://velorama.nl/
-    retrieved_on: '2025-11-29T15:47:25.907146+00:00'
-    xpath: /html/head/title
-    html_file: web/0286/velorama.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:04.558471+00:00'
  - claim_type: org_name
    claim_value: Nationaal Fietsmuseum Velorama
    raw_value: Nationaal Fietsmuseum Velorama
@ -919,6 +909,14 @@ web_claims:
    xpath_match_score: 0.9
    extraction_method: h1_tag
    extraction_timestamp: '2025-12-01T10:45:04.559245+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Nationaal Fietsmuseum Velorama
--- a/data/nde/enriched/entries/0295_Q121900753.yaml
+++ b/data/nde/enriched/entries/0295_Q121900753.yaml
@ -533,18 +533,8 @@ identifiers:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:06.876921+00:00'
  source_archive: web/0295/museumaandea.nl
-  claims_count: 9
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home - Museum aan de A
-    source_url: https://museumaandea.nl/
-    retrieved_on: '2025-11-29T15:49:11.715226+00:00'
-    xpath: /html/head/title
-    html_file: web/0295/museumaandea.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:06.876192+00:00'
  - claim_type: description_short
    claim_value: Museum van, door en over Groningers.  Kijk voor je bezoek altijd
      op onze website voor de actuele tentoonstellingen.
@ -627,6 +617,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:06.876793+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Museum aan de A
--- a/data/nde/enriched/entries/0309_Q81181191.yaml
+++ b/data/nde/enriched/entries/0309_Q81181191.yaml
@ -441,18 +441,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:10.510345+00:00'
  source_archive: web/0309/eemsdelta.nl
-  claims_count: 16
+  claims_count: 11
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Eemsdelta
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:22.610004+00:00'
-    xpath: /html/head/title
-    html_file: web/0309/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.509614+00:00'
  - claim_type: org_name
    claim_value: Gemeente Eemsdelta
    raw_value: Gemeente Eemsdelta
@ -473,46 +463,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:10.509633+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:22.610004+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0309/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.509642+00:00'
-  - claim_type: org_name
-    claim_value: X
-    raw_value: X
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:22.610004+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0309/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.509647+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:22.610004+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0309/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.509651+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:22.610004+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[4]/a/svg/title
-    html_file: web/0309/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.509655+00:00'
  - claim_type: org_name
    claim_value: Youtube
    raw_value: Youtube
@ -603,6 +553,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:10.510187+00:00'
+  removed_invalid_claims:
+  - removed_count: 5
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Appingedam
--- a/data/nde/enriched/entries/0311_Q81181383.yaml
+++ b/data/nde/enriched/entries/0311_Q81181383.yaml
@ -438,18 +438,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:10.889962+00:00'
  source_archive: web/0311/westerwolde.nl
-  claims_count: 16
+  claims_count: 11
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Westerwolde
-    source_url: https://www.westerwolde.nl/
-    retrieved_on: '2025-11-29T15:51:25.286603+00:00'
-    xpath: /html/head/title
-    html_file: web/0311/westerwolde.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.888532+00:00'
  - claim_type: org_name
    claim_value: Gemeente Westerwolde
    raw_value: Gemeente Westerwolde
@ -480,46 +470,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:10.888559+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.westerwolde.nl/
-    retrieved_on: '2025-11-29T15:51:25.286603+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0311/westerwolde.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.888572+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.westerwolde.nl/
-    retrieved_on: '2025-11-29T15:51:25.286603+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0311/westerwolde.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.888577+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.westerwolde.nl/
-    retrieved_on: '2025-11-29T15:51:25.286603+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0311/westerwolde.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.888581+00:00'
-  - claim_type: org_name
-    claim_value: X
-    raw_value: X
-    source_url: https://www.westerwolde.nl/
-    retrieved_on: '2025-11-29T15:51:25.286603+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[4]/a/svg/title
-    html_file: web/0311/westerwolde.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:10.888585+00:00'
  - claim_type: org_name
    claim_value: Youtube
    raw_value: Youtube
@ -600,6 +550,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:10.889714+00:00'
+  removed_invalid_claims:
+  - removed_count: 5
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Bellingwedde
--- a/data/nde/enriched/entries/0313_Q81181241.yaml
+++ b/data/nde/enriched/entries/0313_Q81181241.yaml
@ -356,18 +356,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.083942+00:00'
  source_archive: web/0313/eemsdelta.nl
-  claims_count: 16
+  claims_count: 11
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Eemsdelta
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:26.290002+00:00'
-    xpath: /html/head/title
-    html_file: web/0313/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.082770+00:00'
  - claim_type: org_name
    claim_value: Gemeente Eemsdelta
    raw_value: Gemeente Eemsdelta
@ -388,46 +378,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:11.082789+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:26.290002+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0313/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.082798+00:00'
-  - claim_type: org_name
-    claim_value: X
-    raw_value: X
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:26.290002+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0313/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.082803+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:26.290002+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0313/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.082808+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:26.290002+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[4]/a/svg/title
-    html_file: web/0313/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.082812+00:00'
  - claim_type: org_name
    claim_value: Youtube
    raw_value: Youtube
@ -518,6 +468,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.083501+00:00'
+  removed_invalid_claims:
+  - removed_count: 5
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Delfzijl
--- a/data/nde/enriched/entries/0315_Q81181260.yaml
+++ b/data/nde/enriched/entries/0315_Q81181260.yaml
@ -348,18 +348,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.269475+00:00'
  source_archive: web/0315/westerkwartier.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Westerkwartier
-    source_url: https://www.westerkwartier.nl/
-    retrieved_on: '2025-11-29T15:51:27.421565+00:00'
-    xpath: /html/head/title
-    html_file: web/0315/westerkwartier.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.268968+00:00'
  - claim_type: description_short
    claim_value: Op deze website vindt u alle informatie, nieuwsberichten en dienstverlening
      van gemeente Westerkwartier.
@ -412,6 +402,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.269372+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Grootegast
--- a/data/nde/enriched/entries/0316_Q81181282.yaml
+++ b/data/nde/enriched/entries/0316_Q81181282.yaml
@ -353,18 +353,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.373161+00:00'
  source_archive: web/0316/gemeente.groningen.nl
-  claims_count: 31
+  claims_count: 30
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Groningen
-    source_url: https://gemeente.groningen.nl/
-    retrieved_on: '2025-11-29T15:51:35.978903+00:00'
-    xpath: /html/head/title
-    html_file: web/0316/gemeente.groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.372331+00:00'
  - claim_type: org_name
    claim_value: mobiliteit icon
    raw_value: mobiliteit icon
@ -667,6 +657,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.372954+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Haren
--- a/data/nde/enriched/entries/0317_Q81181273.yaml
+++ b/data/nde/enriched/entries/0317_Q81181273.yaml
@ -375,18 +375,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.477554+00:00'
  source_archive: web/0317/midden-groningen.nl
-  claims_count: 12
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Midden-Groningen
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:37.597843+00:00'
-    xpath: /html/head/title
-    html_file: web/0317/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.476796+00:00'
  - claim_type: org_name
    claim_value: Gemeente Midden-Groningen
    raw_value: Gemeente Midden-Groningen
@ -407,36 +397,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:11.476814+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:37.597843+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[1]/a/svg/title
-    html_file: web/0317/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.476823+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:37.597843+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[2]/a/svg/title
-    html_file: web/0317/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.476827+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:37.597843+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[3]/a/svg/title
-    html_file: web/0317/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.476831+00:00'
  - claim_type: org_name
    claim_value: Youtube kanaal
    raw_value: Youtube kanaal
@ -497,6 +457,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.477409+00:00'
+  removed_invalid_claims:
+  - removed_count: 4
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Hoogezand-Sappemeer
--- a/data/nde/enriched/entries/0318_Q81181307.yaml
+++ b/data/nde/enriched/entries/0318_Q81181307.yaml
@ -390,18 +390,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.572721+00:00'
  source_archive: web/0318/westerkwartier.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Westerkwartier
-    source_url: https://www.westerkwartier.nl/
-    retrieved_on: '2025-11-29T15:51:38.210879+00:00'
-    xpath: /html/head/title
-    html_file: web/0318/westerkwartier.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.571982+00:00'
  - claim_type: description_short
    claim_value: Op deze website vindt u alle informatie, nieuwsberichten en dienstverlening
      van gemeente Westerkwartier.
@ -454,6 +444,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.572608+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Leek
--- a/data/nde/enriched/entries/0319_Q81181310.yaml
+++ b/data/nde/enriched/entries/0319_Q81181310.yaml
@ -422,18 +422,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.677180+00:00'
  source_archive: web/0319/eemsdelta.nl
-  claims_count: 16
+  claims_count: 11
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Eemsdelta
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:41.290233+00:00'
-    xpath: /html/head/title
-    html_file: web/0319/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.676253+00:00'
  - claim_type: org_name
    claim_value: Gemeente Eemsdelta
    raw_value: Gemeente Eemsdelta
@ -454,46 +444,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:11.676274+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:41.290233+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[1]/a/svg/title
-    html_file: web/0319/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.676283+00:00'
-  - claim_type: org_name
-    claim_value: X
-    raw_value: X
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:41.290233+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[2]/a/svg/title
-    html_file: web/0319/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.676288+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:41.290233+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[3]/a/svg/title
-    html_file: web/0319/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.676292+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.eemsdelta.nl/home
-    retrieved_on: '2025-11-29T15:51:41.290233+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[4]/ul/li[4]/a/svg/title
-    html_file: web/0319/eemsdelta.nl/pages/home.tmp.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.676296+00:00'
  - claim_type: org_name
    claim_value: Youtube
    raw_value: Youtube
@ -584,6 +534,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.676898+00:00'
+  removed_invalid_claims:
+  - removed_count: 5
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Loppersum
--- a/data/nde/enriched/entries/0320_Q81181318.yaml
+++ b/data/nde/enriched/entries/0320_Q81181318.yaml
@ -318,18 +318,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.780971+00:00'
  source_archive: web/0320/westerkwartier.nl
-  claims_count: 6
+  claims_count: 5
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Westerkwartier
-    source_url: https://www.westerkwartier.nl/
-    retrieved_on: '2025-11-29T15:51:41.935757+00:00'
-    xpath: /html/head/title
-    html_file: web/0320/westerkwartier.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.780253+00:00'
  - claim_type: description_short
    claim_value: Op deze website vindt u alle informatie, nieuwsberichten en dienstverlening
      van gemeente Westerkwartier.
@ -382,6 +372,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.780763+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Marum
--- a/data/nde/enriched/entries/0321_Q81181324.yaml
+++ b/data/nde/enriched/entries/0321_Q81181324.yaml
@ -370,18 +370,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.877032+00:00'
  source_archive: web/0321/midden-groningen.nl
-  claims_count: 12
+  claims_count: 8
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Gemeente Midden-Groningen
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:42.179010+00:00'
-    xpath: /html/head/title
-    html_file: web/0321/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.876362+00:00'
  - claim_type: org_name
    claim_value: Gemeente Midden-Groningen
    raw_value: Gemeente Midden-Groningen
@ -402,36 +392,6 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: title_tag
    extraction_timestamp: '2025-12-01T10:45:11.876380+00:00'
-  - claim_type: org_name
-    claim_value: Facebook
-    raw_value: Facebook
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:42.179010+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[1]/a/svg/title
-    html_file: web/0321/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.876388+00:00'
-  - claim_type: org_name
-    claim_value: Instagram
-    raw_value: Instagram
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:42.179010+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[2]/a/svg/title
-    html_file: web/0321/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.876392+00:00'
-  - claim_type: org_name
-    claim_value: LinkedIn
-    raw_value: LinkedIn
-    source_url: https://www.midden-groningen.nl/
-    retrieved_on: '2025-11-29T15:51:42.179010+00:00'
-    xpath: /html/body/div[2]/div/footer/div/div/div[3]/ul/li[3]/a/svg/title
-    html_file: web/0321/midden-groningen.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.876396+00:00'
  - claim_type: org_name
    claim_value: Youtube kanaal
    raw_value: Youtube kanaal
@ -492,6 +452,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.876893+00:00'
+  removed_invalid_claims:
+  - removed_count: 4
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Menterwolde
--- a/data/nde/enriched/entries/0322_Q81181387.yaml
+++ b/data/nde/enriched/entries/0322_Q81181387.yaml
@ -531,18 +531,8 @@ ghcid:
 web_claims:
  extraction_timestamp: '2025-12-01T10:45:11.991194+00:00'
  source_archive: web/0322/gemeente-oldambt.nl
-  claims_count: 35
+  claims_count: 34
  claims:
-  - claim_type: org_name
-    claim_value: Home
-    raw_value: Home | Oldambt
-    source_url: http://www.gemeente-oldambt.nl
-    retrieved_on: '2025-11-29T15:51:42.548124+00:00'
-    xpath: /html/head/title
-    html_file: web/0322/gemeente-oldambt.nl/pages/index.html
-    xpath_match_score: 1.0
-    extraction_method: title_tag
-    extraction_timestamp: '2025-12-01T10:45:11.990301+00:00'
  - claim_type: org_name
    claim_value: verkiezingen icon
    raw_value: verkiezingen icon
@ -883,6 +873,14 @@ web_claims:
    xpath_match_score: 1.0
    extraction_method: social_link
    extraction_timestamp: '2025-12-01T10:45:11.990987+00:00'
+  removed_invalid_claims:
+  - removed_count: 1
+    audit_timestamp: '2025-12-01'
+    reasons:
+    - share_buttons_as_social
+    - invalid_org_names
+    - empty_claims
+    - spam_content
 custodian_name:
  claim_type: custodian_name
  claim_value: Gemeentearchief Oldambt
--- a/Show more
+++ b/Show more