kempersc/glam
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
glam/data/custodian/NL-ZH-DHA-L-PL.yaml
kempersc 349f31ae6f enrich custodian profiles
2026-01-02 02:10:18 +01:00

578 lines
19 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

original_entry:
plaatsnaam_bezoekadres: Den Haag
organisatie: Passend Lezen
type_organisatie: bibliotheek
isil_code_kb: NL-0774500000
type:
- L
opmerkingen: landelijke bibliotheekorganisatie
entry_index: 1371
processing_timestamp: '2025-11-28T12:19:25.739468+00:00'
kb_enrichment:
source: KB Netherlands Library Network
source_file: KB_Netherlands_ISIL_2025-04-01.xlsx
source_url: https://www.bibliotheeknetwerk.nl/
extraction_date: '2025-11-17T13:02:03.421813+00:00'
enrichment_timestamp: '2025-11-28T12:19:25.739468+00:00'
enrichment_method: automated_integration
isil_code: NL-0774500000
name: Passend Lezen
city: Den Haag
registry: KB Netherlands Library Network
notes: landelijke bibliotheekorganisatie
country: Netherlands
enrichment_status: isil_kb_source
provenance:
schema_version: 1.0.0
generated_at: '2025-11-28T23:47:39.585538+00:00'
sources:
original_entry:
- source_type: nde_csv_registry
data_tier: TIER_1_AUTHORITATIVE
claims_extracted:
- plaatsnaam_bezoekadres
- organisatie
- type_organisatie
- isil_code_kb
- type
- opmerkingen
google_maps:
- source_type: google_maps_api
fetch_timestamp: '2025-11-28T12:24:39.846150+00:00'
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
place_id: ChIJDytDeU23xUcRK7r6yHiAW6E
claims_extracted:
- coordinates
- formatted_address
- address_components
- business_status
- website
- phone
- rating
- opening_hours
genealogiewerkbalk:
- source_type: genealogiewerkbalk_registry
fetch_timestamp: '2025-12-03T14:26:32.904976+00:00'
data_url: https://docs.google.com/spreadsheets/d/1rS_Z5L6L2vvfGLS6eHI8wfyiwB-KUfHEr7W1VNY3rpg/export?format=csv
match_method: plaatsnaam_bezoekadres
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
linkup_timespan:
- source_type: linkup_web_search
fetch_timestamp: '2025-12-15T22:16:57.235520+00:00'
search_query: '"Passend Lezen" Den Haag opgericht OR gesticht OR sinds'
source_urls:
- https://nl.linkedin.com/company/passend-lezen
- https://www.geschiedenisvanzuidholland.nl/verhalen/verhalen/de-geschiedenis-van-den-haag/
- https://haagsgemeentearchief.nl/ontdek-de-stad/verhalen-van-de-stad/het-ontstaan-van-den-haag
- https://nl.wikipedia.org/wiki/Literatuurmuseum
- https://huisvangedichten.nl/
claims_extracted:
- timespan_begin
data_tier: TIER_4_INFERRED
archive_path: data/custodian/web/1371/linkup/linkup_founding_20251215T221657Z.json
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 2025-12-08T23:19:48Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T07:11:20Z
enrichment_source: KB Netherlands Library Network
enrichment_timestamp: '2025-11-28T12:19:25.739468+00:00'
wikidata_enrichment_status: NOT_FOUND
wikidata_search_timestamp: '2025-11-30T17:12:17.758196+00:00'
google_maps_enrichment:
place_id: ChIJDytDeU23xUcRK7r6yHiAW6E
name: Passend Lezen
fetch_timestamp: '2025-11-28T12:24:39.846150+00:00'
api_status: OK
coordinates:
latitude: 52.087972699999995
longitude: 4.320062399999999
formatted_address: Zuid Hollandlaan 7, 2596 AL Den Haag
short_address: Zuid Hollandlaan 7, Den Haag
address_components:
- long_name: '7'
short_name: '7'
types:
- street_number
- long_name: Zuid Hollandlaan
short_name: Zuid Hollandlaan
types:
- route
- long_name: Haagse Hout
short_name: Haagse Hout
types:
- sublocality_level_1
- sublocality
- political
- long_name: Den Haag
short_name: Den Haag
types:
- locality
- political
- long_name: Den Haag
short_name: Den Haag
types:
- administrative_area_level_2
- political
- long_name: Zuid-Holland
short_name: ZH
types:
- administrative_area_level_1
- political
- long_name: Nederland
short_name: NL
types:
- country
- political
- long_name: 2596 AL
short_name: 2596 AL
types:
- postal_code
phone_local: 070 338 1500
phone_international: +31 70 338 1500
website: https://www.passendlezen.nl/
google_place_types:
- point_of_interest
- establishment
business_status: OPERATIONAL
opening_hours:
periods:
- open:
day: 1
hour: 9
minute: 0
close:
day: 1
hour: 12
minute: 0
- open:
day: 1
hour: 13
minute: 0
close:
day: 1
hour: 16
minute: 0
- open:
day: 2
hour: 9
minute: 0
close:
day: 2
hour: 12
minute: 0
- open:
day: 3
hour: 9
minute: 0
close:
day: 3
hour: 12
minute: 0
- open:
day: 3
hour: 13
minute: 0
close:
day: 3
hour: 16
minute: 0
- open:
day: 4
hour: 9
minute: 0
close:
day: 4
hour: 12
minute: 0
- open:
day: 4
hour: 13
minute: 0
close:
day: 4
hour: 16
minute: 0
- open:
day: 5
hour: 9
minute: 0
close:
day: 5
hour: 12
minute: 0
- open:
day: 5
hour: 13
minute: 0
close:
day: 5
hour: 16
minute: 0
weekday_text:
- 'maandag: 09:00–12:00, 13:00–16:00'
- 'dinsdag: 09:00–12:00'
- 'woensdag: 09:00–12:00, 13:00–16:00'
- 'donderdag: 09:00–12:00, 13:00–16:00'
- 'vrijdag: 09:00–12:00, 13:00–16:00'
- 'zaterdag: Gesloten'
- 'zondag: Gesloten'
rating: 3.9
total_ratings: 24
google_maps_url: https://maps.google.com/?cid=11627028119243373099&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
google_maps_status: SUCCESS
google_maps_search_query: Bibliotheek Passend Lezen, Den Haag, Netherlands
ghcid:
ghcid_current: NL-ZH-DHA-L-PL
ghcid_original: NL-ZH-DHA-L-PL
ghcid_uuid: 078a3782-f479-55f6-9f45-e1672de49d21
ghcid_uuid_sha256: 33ec95ca-c538-8946-a4bc-b7da986f8a00
ghcid_numeric: 3741530088562768198
record_id: 019adf94-f32a-7444-954e-27c2dad7dfd9
generation_timestamp: '2025-12-02T14:56:45.615377+00:00'
ghcid_history:
- ghcid: NL-ZH-DHA-L-PL
ghcid_numeric: 3741530088562768198
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: Den Haag
geonames_id: null
geonames_name: null
region_code: ZH
country_code: NL
needs_geonames_entry: true
source_coordinates:
latitude: 52.087972699999995
longitude: 4.320062399999999
source: google_maps
geonames_id: null
identifiers:
- identifier_scheme: GHCID
identifier_value: NL-ZH-DHA-L-PL
- identifier_scheme: GHCID_UUID
identifier_value: 078a3782-f479-55f6-9f45-e1672de49d21
identifier_url: urn:uuid:078a3782-f479-55f6-9f45-e1672de49d21
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 33ec95ca-c538-8946-a4bc-b7da986f8a00
identifier_url: urn:uuid:33ec95ca-c538-8946-a4bc-b7da986f8a00
- identifier_scheme: GHCID_NUMERIC
identifier_value: '3741530088562768198'
- identifier_scheme: RECORD_ID
identifier_value: 019adf94-f32a-7444-954e-27c2dad7dfd9
identifier_url: urn:uuid:019adf94-f32a-7444-954e-27c2dad7dfd9
custodian_name:
claim_type: custodian_name
claim_value: Passend Lezen
source: original_entry
confidence: 0.745
consensus_method: true
sources_checked: 3
sources_matched: 3
extraction_timestamp: '2025-12-02T13:09:20.047866+00:00'
matching_sources:
- source: google_maps
name: Passend Lezen
score: 1.0
- source: web_h1_tag
name: Blijf lezen
score: 0.64
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: '2025-12-03T14:26:32.904591+00:00'
match_method: plaatsnaam_bezoekadres
match_confidence: 1.0
municipality:
name: '''s-Gravenhage'
code: '518'
municipal_archive:
name: Haags Gemeentearchief
website: https://haagsgemeentearchief.nl/
isil: NL-HaHGA
province:
name: Zuid-Holland
code: '28'
provincial_archive:
name: Nationaal Archief
website: https://www.nationaalarchief.nl/
digital_platforms:
- platform_name: Passend Lezen Website
platform_url: https://www.passendlezen.nl/
platform_type: ONLINE_DATABASE
platform_category:
- Organizational website
- Collection catalog
digital_collections: Organizational website with heritage information
technology_stack: Standard web technology
data_standards:
- HTML5
user_services: Catalog search
sustainability_model: Institutional funding
enrichment_timestamp: '2025-12-05T11:36:26.741454+00:00'
source_method: automated_extraction
wikidata_enrichment:
status: NOT_FOUND
fetch_timestamp: '2025-12-06T19:41:57.462479+00:00'
search_query: Passend Lezen
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.LIB
subtype_label: LIBRARY
ontology_class: schema:Library
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /files/netherlands_complete.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-18T17:16:16.902148+00:00'
statement_created_at: '2026-01-01T13:15:31.379876+00:00'
migration_note: Migrated from agent:claude-conversation on 2026-01-01 (ch_annotator.extraction_provenance)
annotation_provenance:
annotation_agent: opencode-claude-sonnet-4
annotation_date: '2025-12-06T21:13:11.947020+00:00'
annotation_method: retroactive CH-Annotator application via batch script
source_file: netherlands_complete.yaml
annotation_metadata:
confidence_score: 1.0
verified: false
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: Passend Lezen
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/netherlands_complete.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-18T17:16:16.902148+00:00'
statement_created_at: '2026-01-01T13:15:31.379890+00:00'
migration_note: Migrated from agent:claude-conversation on 2026-01-01 (entity_claims[0].provenance)
confidence: 1.0
- claim_type: institution_type
claim_value: LIBRARY
property_uri: rdf:type
provenance:
namespace: glam
path: /files/netherlands_complete.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-18T17:16:16.902148+00:00'
statement_created_at: '2026-01-01T13:15:31.379893+00:00'
migration_note: Migrated from agent:claude-conversation on 2026-01-01 (entity_claims[1].provenance)
confidence: 0.95
- claim_type: located_in_city
claim_value: Den Haag
property_uri: schema:addressLocality
provenance:
namespace: glam
path: /files/netherlands_complete.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-18T17:16:16.902148+00:00'
statement_created_at: '2026-01-01T13:15:31.379895+00:00'
migration_note: Migrated from agent:claude-conversation on 2026-01-01 (entity_claims[2].provenance)
confidence: 0.9
integration_note:
integrated_from: netherlands_complete_ch_annotator.yaml
integration_date: '2025-12-06T23:20:34.993129+00:00'
match_type: name
location:
latitude: 52.087972699999995
longitude: 4.320062399999999
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-11-28T12:24:39.846150+00:00'
entity_id: ChIJDytDeU23xUcRK7r6yHiAW6E
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
city: Den Haag
region: Zuid-Holland
region_code: ZH
country: NL
postal_code: 2596 AL
street_address: Zuid Hollandlaan 7, Den Haag
formatted_address: Zuid Hollandlaan 7, 2596 AL Den Haag
normalization_timestamp: '2025-12-09T07:11:20.305678+00:00'
crawl4ai_enrichment:
retrieval_timestamp: '2025-12-14T18:27:04.381984+00:00'
retrieval_agent: crawl4ai
source_url: https://www.passendlezen.nl/
status_code: null
error: Crawl failed with status None
digital_platform_v2:
transformation_metadata:
transformed_from: httpx_beautifulsoup
transformation_date: '2025-12-14T23:46:08.618443+00:00'
transformation_version: '2.1'
source_status_code: 200
primary_platform:
platform_id: primary_website_passendlezen_nl
platform_name: Passend Lezen Website
platform_url: https://www.passendlezen.nl/
platform_type: INSTITUTIONAL_WEBSITE
description: ''
language: nl
og_image: null
favicon: null
timespan:
begin_of_the_begin: '2007-01-01T00:00:00Z'
end_of_the_begin: '2007-01-01T00:00:00Z'
begin_of_the_end: null
end_of_the_end: null
sources:
- 'Linkup web search: https://nl.wikipedia.org/wiki/Blindenbibliotheek'
notes: 'Found via pattern: full_date_nl'
web-enrichments:
extraction_timestamp: '2025-12-13T19:47:29.397315+00:00'
extraction_method: hybrid_llm_pattern_layout_v1
confidence_threshold: 0.6
entities_count: 3
claims:
- entity: Passend Lezen
entity_type: GRP.HER
xpath: /html/head/title
base_confidence: 0.9
layout_score: 0.2
pattern_score: 0.0
final_confidence: 1.0
layout_match: high_conf:head/title
- entity: https://nieuw.passendlezen.nl
entity_type: APP.URL
xpath: /html/head/link[2]
base_confidence: 1.0
layout_score: 0.0
pattern_score: 0.0
final_confidence: 1.0
- entity: Bibliotheekservice Passend Lezen
entity_type: GRP.HER
xpath: /html/body/div/div[2]/header/div[1]/div[1]/a/img
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
web_enrichment:
archive_metadata:
archive_method: httpx_fetch
archive_timestamp: '2025-12-21T10:13:29.338699+00:00'
archive_location: web/NL/ZH/DHA/L/PL
source_url: https://nieuw.passendlezen.nl/
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
claims:
- claim_type: page_title
claim_value: Home | Passend Lezen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/head/title
xpath_match_score: 1.0
extraction_method: title_tag
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: og_title
claim_value: Home | Passend Lezen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/head/meta[10]
xpath_match_score: 1.0
extraction_method: og_title
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: heading_h1
claim_value: Blijf lezen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/main/div[2]/div/div/div/div[1]/div[1]/div/div/div/h1
xpath_match_score: 1.0
extraction_method: h1_tag
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: heading_h1
claim_value: Inloggen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/main/div[3]/div[2]/div/h1
xpath_match_score: 1.0
extraction_method: h1_tag
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: social_facebook
claim_value: https://www.facebook.com/passendlezen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/footer/div[1]/div[2]/div[5]/div/div/ul/li[1]/a
xpath_match_score: 1.0
extraction_method: social_link
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: social_instagram
claim_value: https://www.instagram.com/passendlezen/
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/footer/div[1]/div[2]/div[5]/div/div/ul/li[2]/a
xpath_match_score: 1.0
extraction_method: social_link
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: social_linkedin
claim_value: https://www.linkedin.com/company/passend-lezen
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/footer/div[1]/div[2]/div[5]/div/div/ul/li[4]/a
xpath_match_score: 1.0
extraction_method: social_link
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
- claim_type: social_youtube
claim_value: https://www.youtube.com/channel/UCMjXf9ArnwOz6TpVFDT1wXw
source_url: https://nieuw.passendlezen.nl/
retrieved_on: '2025-12-21T10:13:29.332669+00:00'
xpath: /html/body/div/div/footer/div[1]/div[2]/div[5]/div/div/ul/li[3]/a
xpath_match_score: 1.0
extraction_method: social_link
html_file: web/NL/ZH/DHA/L/PL/nieuw.passendlezen.nl_index.html
logo_enrichment:
enrichment_timestamp: '2025-12-22T12:07:21.498497+00:00'
source_url: https://www.passendlezen.nl
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://3eeb8fe9-6553-11e7-b33e-0287636382f5.s3.eu-west-1.amazonaws.com/3b2a9523-bb27-11ec-88e6-0ab75083a7f7/upload/bosx241fnz5919ilsg8adxfd9iwdhhu0/browser-fav-icon.png
source_url: https://www.passendlezen.nl
css_selector: '[document] > html > head > link:nth-of-type(18)'
retrieved_on: '2025-12-22T12:07:21.498497+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 180x180
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 14
Reference in a new issue View git blame Copy permalink