glam/data/custodian_sample/NL-ZE-WES-S-CW.yaml
2025-12-11 22:32:09 +01:00

413 lines
15 KiB
YAML

original_entry:
plaatsnaam_bezoekadres: Westkapelle
organisatie: Stichting Cultuurbehoud Westkapelle
systeem: ZCBS
reference:
- label: https://www.westkapellecultuurbehoud.nl/
type:
- S
entry_index: 1136
processing_timestamp: '2025-11-27T16:47:17.995202+00:00'
enrichment_status: skipped
provenance:
schema_version: 1.0.0
generated_at: '2025-11-28T23:47:33.372554+00:00'
sources:
original_entry:
- source_type: nde_csv_registry
data_tier: TIER_1_AUTHORITATIVE
claims_extracted:
- plaatsnaam_bezoekadres
- organisatie
- systeem
- reference
- type
google_maps:
- source_type: google_maps_api
fetch_timestamp: '2025-11-28T10:00:10.771479+00:00'
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
place_id: ChIJpapq8ja8xEcRr-AquW8TUpU
claims_extracted:
- coordinates
- formatted_address
- address_components
- business_status
- website
- phone
genealogiewerkbalk:
- source_type: genealogiewerkbalk_registry
fetch_timestamp: '2025-12-03T13:51:52.725346+00:00'
data_url: https://docs.google.com/spreadsheets/d/1rS_Z5L6L2vvfGLS6eHI8wfyiwB-KUfHEr7W1VNY3rpg/export?format=csv
match_method: google_maps_admin2
claims_extracted:
- municipality_name
- municipality_code
- municipal_archive_name
- municipal_archive_website
- municipal_archive_isil
- province_name
- province_code
- provincial_archive_name
- provincial_archive_website
data_tier_summary:
TIER_1_AUTHORITATIVE:
- original_entry (NDE CSV)
TIER_2_VERIFIED:
- wikidata_api
- google_maps_api
- genealogiewerkbalk_registry
TIER_3_CROWD_SOURCED: []
TIER_4_INFERRED:
- website_scrape
- exa_web_search
notes:
- Provenance tracking added retroactively
- claim_level_provenance available in sources section
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:19:42Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T07:10:49Z
skip_reason: no_wikidata_id
google_maps_enrichment:
place_id: ChIJpapq8ja8xEcRr-AquW8TUpU
name: Stichting Cultuurbehoud Westkapelle
fetch_timestamp: '2025-11-28T10:00:10.771479+00:00'
api_status: OK
coordinates:
latitude: 51.5311658
longitude: 3.4426704
formatted_address: Beatrixstraat 8, 4361 EG Westkapelle
short_address: Beatrixstraat 8, Westkapelle
address_components:
- long_name: '8'
short_name: '8'
types:
- street_number
- long_name: Beatrixstraat
short_name: Beatrixstraat
types:
- route
- long_name: Westkapelle
short_name: Westkapelle
types:
- locality
- political
- long_name: Veere
short_name: Veere
types:
- administrative_area_level_2
- political
- long_name: Zeeland
short_name: ZE
types:
- administrative_area_level_1
- political
- long_name: Nederland
short_name: NL
types:
- country
- political
- long_name: 4361 EG
short_name: 4361 EG
types:
- postal_code
phone_local: 0118 572 169
phone_international: +31 118 572 169
website: http://www.westkapellecultuurbehoud.nl/
google_place_types:
- point_of_interest
- establishment
business_status: OPERATIONAL
google_maps_url: https://maps.google.com/?cid=10759683830310428847&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
street_view_url: https://maps.googleapis.com/maps/api/streetview?size=600x400&location=51.5311658,3.4426704&key=AIzaSyAHuazNth9ZvfRFYk5-v49CwXwhABH8Ri0
icon_mask_uri: https://maps.gstatic.com/mapfiles/place_api/icons/v2/generic_pinlet
icon_background_color: '#7B9EB0'
utc_offset_minutes: 60
google_maps_status: SUCCESS
google_maps_search_query: Stichting Cultuurbehoud Westkapelle, Westkapelle, Netherlands
web_enrichment:
web_archives:
- url: https://www.westkapellecultuurbehoud.nl/
directory: web/1136/westkapellecultuurbehoud.nl
pages_archived: 1
archive_method: wget_warc_deep
warc_file: archive.warc.gz
warc_size_bytes: 13087
warc_format: ISO 28500
full_site_archive_timestamp: '2025-11-29T18:16:59.911950+00:00'
zcbs_enrichment:
zcbs_id: 58
zcbs_name: Stichting Cultuurbehoud Westkapelle
platform_urls:
photos: http://www.westkapelle-beeldbank.nl/cgi-bin/beeldbank.pl
enrichment_timestamp: '2025-11-30T19:09:01.327394+00:00'
source: https://www.dezijpe.nl/cgi-bin/boerderij.pl?misc=90
match_score: 1.0
ghcid:
ghcid_current: NL-ZE-WES-S-CW
ghcid_original: NL-ZE-WES-S-CW
ghcid_uuid: 00d5e972-8dbe-5d50-8bd6-bc225c578a11
ghcid_uuid_sha256: 41a2714f-7b9a-8f31-8078-f0b3b6e5a420
ghcid_numeric: 4729467144882491185
record_id: 019adf94-ce2d-7e28-bc85-c855d9e90847
generation_timestamp: '2025-12-02T14:56:45.615377+00:00'
ghcid_history:
- ghcid: NL-ZE-WES-S-CW
ghcid_numeric: 4729467144882491185
valid_from: '2025-12-02T14:56:45.615377+00:00'
valid_to: null
reason: GHCID regenerated with Google Maps locality fix (Dec 2025)
location_resolution:
method: GOOGLE_MAPS_LOCALITY
google_maps_locality: Westkapelle
geonames_id: 2744642
geonames_name: Westkapelle
feature_code: PPL
population: 2515
admin1_code: '10'
region_code: ZE
country_code: NL
source_coordinates:
latitude: 51.5311658
longitude: 3.4426704
source: google_maps
geonames_id: 2744642
identifiers:
- identifier_scheme: GHCID
identifier_value: NL-ZE-WES-S-CW
- identifier_scheme: GHCID_UUID
identifier_value: 00d5e972-8dbe-5d50-8bd6-bc225c578a11
identifier_url: urn:uuid:00d5e972-8dbe-5d50-8bd6-bc225c578a11
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 41a2714f-7b9a-8f31-8078-f0b3b6e5a420
identifier_url: urn:uuid:41a2714f-7b9a-8f31-8078-f0b3b6e5a420
- identifier_scheme: GHCID_NUMERIC
identifier_value: '4729467144882491185'
- identifier_scheme: RECORD_ID
identifier_value: 019adf94-ce2d-7e28-bc85-c855d9e90847
identifier_url: urn:uuid:019adf94-ce2d-7e28-bc85-c855d9e90847
web_claims:
extraction_timestamp: '2025-12-02T08:51:18.090144+00:00'
source_archive: web/1136/westkapellecultuurbehoud.nl
claims_count: 14
claims:
- claim_type: org_name
claim_value: Home
raw_value: Home - Stichting Cultuurbehoud Westkapelle
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/title
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: title_tag
extraction_timestamp: '2025-12-02T08:51:18.075487+00:00'
- claim_type: email
claim_value: info@westkapellecultuurbehoud.nl
raw_value: info@westkapellecultuurbehoud.nl
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/main/section/div/div/p[4]/a
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: mailto_link
extraction_timestamp: '2025-12-02T08:51:18.075905+00:00'
- claim_type: social_facebook
claim_value: https://www.facebook.com/westkapellecultuurbehoud/
raw_value: https://www.facebook.com/westkapellecultuurbehoud/
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/footer/div[1]/div/div/div[4]/nav/a[1]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: social_link
extraction_timestamp: '2025-12-02T08:51:18.076310+00:00'
- claim_type: social_instagram
claim_value: https://www.instagram.com/cultuurbehoudwestkapelle/
raw_value: https://www.instagram.com/cultuurbehoudwestkapelle/
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/footer/div[1]/div/div/div[4]/nav/a[2]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: social_link
extraction_timestamp: '2025-12-02T08:51:18.076318+00:00'
- claim_type: org_name
claim_value: Stichting Cultuurbehoud Westkapelle
raw_value: Stichting Cultuurbehoud Westkapelle
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/header/section/div[1]/div[1]/div/div/div/h1
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 0.9
extraction_method: h1_tag
extraction_timestamp: '2025-12-02T08:51:18.076366+00:00'
- claim_type: gallery_detected
claim_value: swiper
raw_value: 'swiper: 12 elements'
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/header/section/div[1]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 0.85
extraction_method: gallery_pattern
extraction_timestamp: '2025-12-02T08:51:18.080176+00:00'
- claim_type: image_count
claim_value: '9'
raw_value: 9 images in swiper container
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/header/section/div[1]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 0.8
extraction_method: gallery_image_count
extraction_timestamp: '2025-12-02T08:51:18.080330+00:00'
- claim_type: page_title
claim_value: Home - Stichting Cultuurbehoud Westkapelle
raw_value: Home - Stichting Cultuurbehoud Westkapelle
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/title
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: title_tag_full
extraction_timestamp: '2025-12-02T08:51:18.080500+00:00'
- claim_type: favicon
claim_value: /public/img/favicon-32x32.png
raw_value: sizes=32x32, type=image/png
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/link[2]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: favicon_link
extraction_timestamp: '2025-12-02T08:51:18.080541+00:00'
- claim_type: favicon
claim_value: /public/img/favicon-16x16.png
raw_value: sizes=16x16, type=image/png
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/link[3]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: favicon_link
extraction_timestamp: '2025-12-02T08:51:18.080546+00:00'
- claim_type: favicon
claim_value: /public/img/favicon.ico
raw_value: /public/img/favicon.ico
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/link[6]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: favicon_link
extraction_timestamp: '2025-12-02T08:51:18.080579+00:00'
- claim_type: favicon
claim_value: /public/img/apple-touch-icon.png
raw_value: sizes=180x180
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/link[1]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: favicon_link
extraction_timestamp: '2025-12-02T08:51:18.080614+00:00'
- claim_type: favicon
claim_value: /public/img/safari-pinned-tab.svg
raw_value: /public/img/safari-pinned-tab.svg
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/head/link[5]
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: favicon_link
extraction_timestamp: '2025-12-02T08:51:18.080618+00:00'
- claim_type: ui_signup
claim_value: https://www.westkapellecultuurbehoud.nl/genealogie-westkapelle/genealogie
raw_value: text=register begraafplaats westkapelle, pattern=register
source_url: https://www.westkapellecultuurbehoud.nl/
retrieved_on: '2025-11-29T18:16:59.890825+00:00'
xpath: /html/body/header/section/div[2]/nav/div/div/div[2]/ul/li[10]/ul/li[2]/a
html_file: web/1136/westkapellecultuurbehoud.nl/pages/index.html
xpath_match_score: 1.0
extraction_method: signup_button
extraction_timestamp: '2025-12-02T08:51:18.082161+00:00'
custodian_name:
claim_type: custodian_name
claim_value: Cultuurbehoud Westkapelle
source: web_h1_tag
confidence: 0.815
consensus_method: true
sources_checked: 3
sources_matched: 3
extraction_timestamp: '2025-12-02T13:08:56.546906+00:00'
matching_sources:
- source: google_maps
name: Cultuurbehoud Westkapelle
score: 1.0
- source: original_entry
name: Cultuurbehoud Westkapelle
score: 1.0
previous_value: Stichting Cultuurbehoud Westkapelle
previous_source: web_h1_tag
custodian_legal_name:
claim_type: legal_name
claim_value: Stichting Cultuurbehoud Westkapelle
extraction_timestamp: '2025-12-02T13:08:56.546915+00:00'
note: Legal form detected in source name (e.g., Stichting, Vereniging, B.V.)
genealogiewerkbalk_enrichment:
source: Genealogiewerkbalk.nl Municipality Archives Registry
source_url: https://www.genealogiewerkbalk.nl/archieven.html
data_url: https://docs.google.com/spreadsheets/d/1rS_Z5L6L2vvfGLS6eHI8wfyiwB-KUfHEr7W1VNY3rpg/export?format=csv
data_tier: TIER_2_VERIFIED
enrichment_timestamp: '2025-12-03T13:51:52.725333+00:00'
match_method: google_maps_admin2
match_confidence: 0.95
municipality:
name: Veere
code: '717'
municipal_archive:
name: Zeeuws Archief
website: https://www.zeeuwsarchief.nl/
isil: NL-MdbZA
province:
name: Zeeland
code: '29'
provincial_archive:
name: Zeeuws Archief
website: https://www.zeeuwsarchief.nl/
digital_platforms:
- platform_name: Stichting Cultuurbehoud Westkapelle Website
platform_url: http://www.westkapellecultuurbehoud.nl/
platform_type: WEBSITE
platform_category:
- Organizational website
digital_collections: Organizational website
technology_stack: ZCBS
data_standards:
- HTML5
user_services: General information, Contact
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:22:14.994875+00:00'
source_method: automated_extraction
wikidata_enrichment:
status: NOT_FOUND
fetch_timestamp: '2025-12-06T19:41:46.797411+00:00'
search_query: Cultuurbehoud Westkapelle
location:
latitude: 51.5311658
longitude: 3.4426704
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-11-28T10:00:10.771479+00:00'
entity_id: ChIJpapq8ja8xEcRr-AquW8TUpU
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
city: Westkapelle
region: Zeeland
region_code: ZE
country: NL
postal_code: 4361 EG
street_address: Beatrixstraat 8, Westkapelle
formatted_address: Beatrixstraat 8, 4361 EG Westkapelle
geonames_id: 2744642
geonames_name: Westkapelle
feature_code: PPL
normalization_timestamp: '2025-12-09T07:10:49.669438+00:00'