glam/data/custodian/NL-OV-ALM-A-FA.yaml
2026-01-18 01:23:32 +01:00

531 lines
17 KiB
YAML

original_entry:
plaatsnaam_bezoekadres: Oldenzaal
organisatie: Twents Fotoarchief in Oldenzaal
isil_code_na: NL-OdzTFA
reference:
- label: https://www.fotoarchieftwente.nl/
type:
- A
entry_index: 986
processing_timestamp: '2025-11-27T16:43:07.696937+00:00'
enrichment_status: skipped
provenance:
schema_version: 1.0.0
generated_at: '2025-11-28T23:47:29.923577+00:00'
sources:
original_entry:
- source_type: nde_csv_registry
data_tier: TIER_1_AUTHORITATIVE
claims_extracted:
- plaatsnaam_bezoekadres
- organisatie
- isil-code_na
- reference
- type
google_maps:
- source_type: google_maps_api
fetch_timestamp: '2025-11-28T09:58:37.551897+00:00'
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
place_id: ChIJ6TVm8zsGuEcRvCIRsuUSrdg
claims_extracted:
- coordinates
- formatted_address
- address_components
- business_status
- rating
- reviews
genealogiewerkbalk:
- source_type: genealogiewerkbalk_registry
fetch_timestamp: '2025-12-03T13:51:38.292089+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: '2025-12-15T20:10:33.390553+00:00'
search_query: '"Fotoarchief" Almelo opgericht OR gesticht OR sinds'
source_urls:
- https://almelo.bestuurlijkeinformatie.nl/Document/View/4461ee11-01bc-4f7e-87df-5450ab8acfd6
- https://indebuurt.nl/almelo/genieten-van/bijzonder-deze-almelose-fotos-komen-uit-het-archief-van-het-rijksmuseum~302582/
- https://www.nationaalarchief.nl/onderzoeken/archief/4.AANW/invnr/695
- https://www.nationaalarchief.nl/onderzoeken/archief/4.KIVI/invnr/@V~1~964
- https://www.archivesportaleurope.net/advanced-search/search-in-archives/results-(archives)/?repositoryCode=NL-ZlHCO&term=Sm?rn?&levelName=archdesc&t=fa&recordId=0214&c=F2777934
claims_extracted:
- timespan_begin
data_tier: TIER_4_INFERRED
archive_path: data/custodian/web/0986/linkup/linkup_founding_20251215T201033Z.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 normalized on 2025-12-09T13:13:52Z
skip_reason: no_wikidata_id
google_maps_enrichment:
place_id: ChIJ6TVm8zsGuEcRvCIRsuUSrdg
name: Stichting Fotoarchief
fetch_timestamp: '2025-11-28T09:58:37.551897+00:00'
api_status: OK
coordinates:
latitude: 52.358778099999995
longitude: 6.667135999999999
formatted_address: Herengracht 16, 7607 BR Almelo
short_address: Herengracht 16, Almelo
address_components:
- long_name: '16'
short_name: '16'
types:
- street_number
- long_name: Herengracht
short_name: Herengracht
types:
- route
- long_name: Almelo
short_name: Almelo
types:
- locality
- political
- long_name: Almelo
short_name: Almelo
types:
- administrative_area_level_2
- political
- long_name: Overijssel
short_name: OV
types:
- administrative_area_level_1
- political
- long_name: Nederland
short_name: NL
types:
- country
- political
- long_name: 7607 BR
short_name: 7607 BR
types:
- postal_code
google_place_types:
- point_of_interest
- establishment
primary_type: point_of_interest
business_status: OPERATIONAL
rating: 4
total_ratings: 1
reviews:
- author_name: Wim Dommerholt
author_uri: https://www.google.com/maps/contrib/111247606033823149368/reviews
rating: 4
relative_time_description: 6 jaar geleden
text: null
publish_time: '2019-06-11T18:09:32.290502Z'
google_maps_url: https://maps.google.com/?cid=15613156260907655868&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
street_view_url: https://maps.googleapis.com/maps/api/streetview?size=600x400&location=52.358778099999995,6.667135999999999&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: Twents Fotoarchief in Oldenzaal, Oldenzaal, Netherlands
web_enrichment:
web_archives:
- url: https://www.fotoarchieftwente.nl/
directory: web/0986/fotoarchieftwente.nl
pages_archived: 1
archive_method: wget_warc_deep
warc_file: archive.warc.gz
warc_size_bytes: 4886
warc_format: ISO 28500
full_site_archive_timestamp: '2025-11-29T17:41:51.556843+00:00'
nan_isil_enrichment:
source: Nationaal Archief ISIL Registry
source_file: ISIL-codes_2025-11-06.yaml
source_url: https://www.nationaalarchief.nl/isil
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-17T12:27:31.711952+00:00'
enrichment_timestamp: '2025-11-30T09:57:00.894497+00:00'
enrichment_method: fuzzy_name_city_match
match_confidence: 1.0
isil_code: NL-OdzTFA
nan_name: Twents Fotoarchief in Oldenzaal
nan_city: Oldenzaal
nan_toegekend_op: '2016-11-17'
nan_opmerking: ''
identifiers:
- identifier_scheme: ISIL
identifier_value: NL-OdzTFA
identifier_url: https://isil.org/NL-OdzTFA
assigned_date: '2016-11-17'
source: Nationaal Archief ISIL Registry 2025-11-06
- identifier_scheme: GHCID
identifier_value: NL-OV-ALM-A-FA
- identifier_scheme: GHCID_UUID
identifier_value: f9849d53-e06b-5b66-b799-68c66f69c34d
identifier_url: urn:uuid:f9849d53-e06b-5b66-b799-68c66f69c34d
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 86fdbed9-d35e-81cd-9f3f-d23dcf9a9067
identifier_url: urn:uuid:86fdbed9-d35e-81cd-9f3f-d23dcf9a9067
- identifier_scheme: GHCID_NUMERIC
identifier_value: '9727140612953522637'
- identifier_scheme: RECORD_ID
identifier_value: 019adf94-b42d-71eb-aacd-608846b8a0fe
identifier_url: urn:uuid:019adf94-b42d-71eb-aacd-608846b8a0fe
wikidata_enrichment:
wikidata_entity_id: Q121225126
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-09T12:18:31.421888+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P131
- P856
- P625
wikidata_labels:
nl: Stadsarchief Oldenzaal
en: Stadsarchief Oldenzaal
sl: Mestni arhiv Oldenzaal
wikidata_label_en: Stadsarchief Oldenzaal
wikidata_label_nl: Stadsarchief Oldenzaal
wikidata_descriptions:
nl: gemeentelijk archief van Oldenzaal, Nederland
en: municipal archive of Oldenzaal, the Netherlands
sl: mestni arhiv v Oldenzaalu na Nizozemskem
wikidata_description_en: municipal archive of Oldenzaal, the Netherlands
wikidata_aliases:
nl:
- Gemeentearchief Oldenzaal
en:
- Gemeentearchief Oldenzaal
sl:
- Stadsarchief Oldenzaal
wikidata_classification:
instance_of: &id001
- id: Q604177
label: Municipal Archive
description: accumulation of historical records of a town or city
wikidata_instance_of: *id001
wikidata_location:
country: &id002
id: Q55
label: Netherlands
description: country in Northwestern Europe with territories in the Caribbean
located_in_admin_entity: &id003
id: Q10016
label: Oldenzaal
description: municipality in the Netherlands
coordinates: &id004
latitude: 52.312399
longitude: 6.9304488
precision: 1.0e-07
wikidata_country: *id002
wikidata_located_in: *id003
wikidata_coordinates: *id004
wikidata_web:
official_website: https://www.oldenzaal.nl/stadsarchief
wikidata_official_website: https://www.oldenzaal.nl/stadsarchief
ghcid:
ghcid_current: NL-OV-ALM-A-FA
ghcid_original: NL-OV-ALM-A-FA
ghcid_uuid: f9849d53-e06b-5b66-b799-68c66f69c34d
ghcid_uuid_sha256: 86fdbed9-d35e-81cd-9f3f-d23dcf9a9067
ghcid_numeric: 9727140612953522637
record_id: 019adf94-b42d-71eb-aacd-608846b8a0fe
generation_timestamp: '2025-12-02T14:56:45.615377+00:00'
ghcid_history:
- ghcid: NL-OV-ALM-A-FA
ghcid_numeric: 9727140612953522637
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: Almelo
geonames_id: 2759887
geonames_name: Almelo
feature_code: PPL
population: 72725
admin1_code: '15'
region_code: OV
country_code: NL
source_coordinates:
latitude: 52.358778099999995
longitude: 6.667135999999999
source: google_maps
geonames_id: 2759887
custodian_name:
claim_type: custodian_name
claim_value: Fotoarchief
source: google_maps
confidence: 0.837
consensus_method: true
sources_checked: 4
sources_matched: 4
extraction_timestamp: '2025-12-02T13:08:39.864596+00:00'
matching_sources:
- source: nan_isil
name: Twents Fotoarchief in Oldenzaal
score: 1.0
- source: original_entry
name: Twents Fotoarchief in Oldenzaal
score: 1.0
- source: web_title_tag
name: Fotoarchief Twente
score: 1.0
previous_value: Stichting Fotoarchief
previous_source: google_maps
custodian_legal_name:
claim_type: legal_name
claim_value: Stichting Fotoarchief
extraction_timestamp: '2025-12-02T13:08:39.864603+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: '2025-12-03T13:51:38.292083+00:00'
match_method: plaatsnaam_bezoekadres
match_confidence: 1.0
municipality:
name: Oldenzaal
code: '173'
municipal_archive:
name: Stadsarchief Oldenzaal
website: https://www.oldenzaal.nl/stadsarchief
isil: null
isil_note: geenSO
province:
name: Overijssel
code: '23'
provincial_archive:
name: Collectie Overijssel
website: https://collectieoverijssel.nl/
location:
latitude: 52.358778099999995
longitude: 6.667135999999999
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-11-28T09:58:37.551897+00:00'
entity_id: ChIJ6TVm8zsGuEcRvCIRsuUSrdg
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
city: Almelo
region: Overijssel
region_code: OV
country: NL
postal_code: 7607 BR
street_address: Herengracht 16, Almelo
formatted_address: Herengracht 16, 7607 BR Almelo
geonames_id: 2759887
geonames_name: Almelo
feature_code: PPL
normalization_timestamp: '2025-12-09T13:13:52.239315+00:00'
digital_platform_v2:
transformation_metadata:
transformed_from: httpx_beautifulsoup
transformation_date: '2025-12-15T00:00:36.062377+00:00'
transformation_version: '2.1'
source_status_code: 200
primary_platform:
platform_id: primary_website_fotoarchieftwente_nl
platform_name: Fotoarchief Twente Website
platform_url: https://www.fotoarchieftwente.nl/
platform_type: DIGITAL_ARCHIVE
description: ''
language: en
og_image: null
favicon: null
timespan:
begin_of_the_begin: '2020-12-11T00:00:00Z'
end_of_the_begin: '2020-12-11T00:00:00Z'
begin_of_the_end: null
end_of_the_end: null
sources:
- 'Linkup web search: http://aavisie.nl/nieuws/actua/30087/Peter+Leeuwen+schenkt+fotoarchief+aan+Stadsmuseum/'
notes: 'Found via pattern: full_date_nl'
web_enrichments:
extraction_timestamp: '2025-12-13T19:46:05.046280+00:00'
extraction_method: hybrid_llm_pattern_layout_v1
confidence_threshold: 0.6
entities_count: 18
claims:
- entity: Stichting Digitalisering Historische Twentse Kranten & De Twentsche Courant
Tubantia
entity_type: GRP.ASS
xpath: /html/body/div/section/div[1]/p
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.15
final_confidence: 1.0
pattern_match: \b(vereniging|stichting|genootschap|kring)\b
- entity: Oldenzaal
entity_type: TOP.SET
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.15
final_confidence: 1.0
pattern_match: ^[A-Z][a-z]+$
- entity: Fotoarchief Twente
entity_type: APP.TIT
xpath: /html/head/title
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: FOTOARCHIEFHEADER.png
entity_type: THG.ART
xpath: /html/body/div/section/div[3]/img
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: fotoarchief Twente
entity_type: WRK.COL
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: https://publiek.fotoarchieftwente.nl/
entity_type: APP.URL
xpath: /html/body/div/div[1]/p[2]/a
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: '400.000'
entity_type: QTY.CNT
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: Anderhalf miljoen
entity_type: QTY.CNT
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.95
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.95
- entity: Twente
entity_type: TOP.REG
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.9
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.9
wikidata_id: Q1455944
wikidata_label: Twente
- entity: zwartwitfoto's
entity_type: THG.PHO
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.9
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.9
- entity: Tubantia
entity_type: GRP.INF
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.9
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.9
- entity: de Twentsche Courant
entity_type: WRK.SER
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.9
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.9
- entity: De Twentsche Courant Tubantia
entity_type: WRK.SER
xpath: /html/body/div/section/div[1]/p
base_confidence: 0.85
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.85
- entity: een groep enthousiaste vrijwilligers
entity_type: GRP.INF
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: Anderhalf miljoen
entity_type: TMP.DRL
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: vervlogen tijden
entity_type: TMP.DRL
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: Zeven jaar geleden
entity_type: TMP.DRL
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: Inmiddels
entity_type: TMP.DRL
xpath: /html/body/div/div[1]/p[1]
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
wikidata_linking_timestamp: '2025-12-13T23:04:56.626076'
logo_enrichment:
enrichment_timestamp: '2025-12-22T10:05:16.967902+00:00'
source_url: https://www.oldenzaal.nl/stadsarchief
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.oldenzaal.nl/images/logo2d85cd83dc936621.svg
source_url: https://www.oldenzaal.nl/stadsarchief
css_selector: '#__next > div > div.jss1.is-home:nth-of-type(2) > header.jss6.hero-has-image
> div.jss18.wrapper > div.MuiBox-root.jss116 > div.MuiBox-root.jss117 > h1.jss7
> img'
retrieved_on: '2025-12-22T10:05:16.967902+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: Gemeente Oldenzaal logo
- claim_type: favicon_url
claim_value: https://www.oldenzaal.nl/images/favicond6314f62c97fe9ba.ico
source_url: https://www.oldenzaal.nl/stadsarchief
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-22T10:05:16.967902+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1