glam/data/custodian/NL-NH-AMS-S-WH.yaml
2026-01-18 01:23:32 +01:00

478 lines
17 KiB
YAML

original_entry:
organisatie: Stichting Weeshuisjes
samenwerkingsverband_platform: Brabant Cloud
systeem: Vitec Maior
linked_data: nee
reference:
- label: https://www.weeshuisjes.nl/
type:
- S
entry_index: 593
processing_timestamp: '2025-11-27T15:28:09.260848+00:00'
enrichment_status: skipped
provenance:
schema_version: 1.0.0
generated_at: '2025-11-28T23:47:20.025569+00:00'
sources:
original_entry:
- source_type: nde_csv_registry
data_tier: TIER_1_AUTHORITATIVE
claims_extracted:
- organisatie
- samenwerkingsverband_platform
- systeem
- linked_data
- reference
- type
google_maps:
- source_type: google_maps_api
fetch_timestamp: '2025-11-28T09:54:38.063681+00:00'
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
place_id: ChIJ__-WvekJxkcR1lmeTclWQQI
claims_extracted:
- coordinates
- formatted_address
- address_components
- business_status
- rating
- reviews
genealogiewerkbalk:
- source_type: genealogiewerkbalk_registry
fetch_timestamp: '2025-12-03T13:50:28.861943+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
linkup_timespan:
- source_type: linkup_web_search
fetch_timestamp: '2025-12-15T19:40:39.950249+00:00'
search_query: '"Het Weeshuis" Amsterdam opgericht OR gesticht OR sinds'
source_urls:
- https://tussentaalenbeeld.nl/weeshuis.html
- https://amsterdamsverleden.nl/burgerweeshuis/
- https://www.amsterdamhv.nl/wiki/weeskinderen.html
- https://www.uitdeoudekoektrommel.com/armvoogdij-vondelingen-en-weeskinderen-gestichten-en-gasthuizen-en-voogden/
- https://hart.amsterdam/nl/page/4175/in-het-weeshuis
claims_extracted:
- timespan_begin
data_tier: TIER_4_INFERRED
archive_path: data/custodian/web/0593/linkup/linkup_founding_20251215T194039Z.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 2025-12-08T23:18:11Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T07:06:10Z
skip_reason: no_wikidata_id
google_maps_enrichment:
place_id: ChIJ__-WvekJxkcR1lmeTclWQQI
name: Het Weeshuis
fetch_timestamp: '2025-11-28T09:54:38.063681+00:00'
api_status: OK
coordinates:
latitude: 52.3652726
longitude: 4.885896
formatted_address: Kerkstraat 51-53, 1017 GC Amsterdam
short_address: Kerkstraat 51-53, Amsterdam
address_components:
- long_name: 51-53
short_name: 51-53
types:
- street_number
- long_name: Kerkstraat
short_name: Kerkstraat
types:
- route
- long_name: Amsterdam-Centrum
short_name: Amsterdam-Centrum
types:
- sublocality_level_1
- sublocality
- political
- long_name: Amsterdam
short_name: Amsterdam
types:
- locality
- political
- long_name: Amsterdam
short_name: Amsterdam
types:
- administrative_area_level_2
- political
- long_name: Noord-Holland
short_name: NH
types:
- administrative_area_level_1
- political
- long_name: Nederland
short_name: NL
types:
- country
- political
- long_name: 1017 GC
short_name: 1017 GC
types:
- postal_code
google_place_types:
- point_of_interest
- establishment
primary_type: point_of_interest
business_status: OPERATIONAL
rating: 5
total_ratings: 1
reviews:
- author_name: philipp Link
author_uri: https://www.google.com/maps/contrib/100709152378303308658/reviews
rating: 5
relative_time_description: 2 jaar geleden
text: Freddy is echt een aardige kerel! Een absolute aanrader🍃
publish_time: '2023-09-13T08:35:11.085069Z'
google_maps_url: https://maps.google.com/?cid=162506484152687062&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
street_view_url: https://maps.googleapis.com/maps/api/streetview?size=600x400&location=52.3652726,4.885896&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 Weeshuisjes, Netherlands
web_enrichment:
web_archives:
- url: https://www.weeshuisjes.nl/
directory: web/0593/weeshuisjes.nl
pages_archived: 31
archive_method: wget_warc_deep
warc_file: archive.warc.gz
warc_size_bytes: 664152
warc_format: ISO 28500
full_site_archive_timestamp: '2025-11-29T16:43:40.783308+00:00'
ghcid:
ghcid_current: NL-NH-AMS-S-WH
ghcid_original: NL-NH-AMS-S-WH
ghcid_uuid: 27c67389-99ce-577b-951c-3c7dc1ecea51
ghcid_uuid_sha256: dcdd4c1c-ec57-8751-8289-5ba69e90f3d2
ghcid_numeric: 15914960345305163601
record_id: 019adf94-6887-72d7-a042-f4ba0f7652a2
generation_timestamp: '2025-12-02T14:56:45.615377+00:00'
ghcid_history:
- ghcid: NL-NH-AMS-S-WH
ghcid_numeric: 15914960345305163601
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: Amsterdam
geonames_id: 2759794
geonames_name: Amsterdam
feature_code: PPLC
population: 741636
admin1_code: '07'
region_code: NH
country_code: NL
source_coordinates:
latitude: 52.3652726
longitude: 4.885896
source: google_maps
geonames_id: 2759794
identifiers:
- identifier_scheme: GHCID
identifier_value: NL-NH-AMS-S-WH
- identifier_scheme: GHCID_UUID
identifier_value: 27c67389-99ce-577b-951c-3c7dc1ecea51
identifier_url: urn:uuid:27c67389-99ce-577b-951c-3c7dc1ecea51
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: dcdd4c1c-ec57-8751-8289-5ba69e90f3d2
identifier_url: urn:uuid:dcdd4c1c-ec57-8751-8289-5ba69e90f3d2
- identifier_scheme: GHCID_NUMERIC
identifier_value: '15914960345305163601'
- identifier_scheme: RECORD_ID
identifier_value: 019adf94-6887-72d7-a042-f4ba0f7652a2
identifier_url: urn:uuid:019adf94-6887-72d7-a042-f4ba0f7652a2
custodian_name:
claim_type: custodian_name
claim_value: Het Weeshuis
source: google_maps
confidence: 0.459
consensus_method: true
sources_checked: 29
sources_matched: 4
extraction_timestamp: '2025-12-02T13:07:53.051053+00:00'
matching_sources:
- source: original_entry
name: Weeshuisjes
score: 0.72
- source: web_title_tag
name: Weeshuisjes Helmond
score: 0.73
- source: web_title_tag
name: Weeshuisjes Den Bosch
score: 0.69
previous_value: Stichting Weeshuisjes
previous_source: original_entry
custodian_legal_name:
claim_type: legal_name
claim_value: Stichting Weeshuisjes
extraction_timestamp: '2025-12-02T13:07:53.051062+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: '2025-12-03T13:50:28.861927+00:00'
match_method: google_maps_admin2
match_confidence: 0.95
municipality:
name: Amsterdam
code: '363'
municipal_archive:
name: Stadsarchief Amsterdam
website: https://archief.amsterdam/
isil: NL-AsdSAA
province:
name: Noord-Holland
code: '27'
provincial_archive:
name: Noord-Hollands Archief
website: https://noord-hollandsarchief.nl/
wikidata_enrichment:
status: NOT_FOUND
fetch_timestamp: '2025-12-06T19:38:16.974443+00:00'
search_query: Het Weeshuis
unesco_ich_enrichment:
country_code: NL
total_elements_in_country: 5
enrichment_timestamp: '2025-12-06T20:20:52.299124+00:00'
elements:
- unesco_ich_id: '1870'
name: Rotterdam Summer Carnival
list_type: RL
list_name: Representative List of the Intangible Cultural Heritage of Humanity
inscription_year: 2023
multinational: false
url: https://ich.unesco.org/en/RL/rotterdam-summer-carnival-01870
description: The Rotterdam Summer Carnival is a multicultural celebration that unites participants from the Caribbean
and European Netherlands, as well as ethnic minority groups from Central and South America and Africa living in the
Netherlands. The event includes a street parade, a brass band competition and a...
- unesco_ich_id: '1979'
name: 'Traditional irrigation: knowledge, technique, and organization'
list_type: RL
list_name: Representative List of the Intangible Cultural Heritage of Humanity
inscription_year: 2023
multinational: true
url: https://ich.unesco.org/en/RL/traditional-irrigation-knowledge-technique-and-organization-01979
description: Traditional irrigation uses gravity and hand-made constructions such as channels and ditches to distribute
water from naturally-occurring water catchment points (such as springs, streams and glaciers) to the fields. Practitioners
choose specific days and periods to manually divert the water, and the...
- unesco_ich_id: '1707'
name: Corso culture, flower and fruit parades in the Netherlands
list_type: RL
list_name: Representative List of the Intangible Cultural Heritage of Humanity
inscription_year: 2021
multinational: false
url: https://ich.unesco.org/en/RL/corso-culture-flower-and-fruit-parades-in-the-netherlands-01707
description: Dating back to the late nineteenth century, a corso is an annual parade of floats or boats decorated with
flowers, fruit, vegetables and, in some cases, people in costumes. Originating in the south of France and Italy, the
practice spread to the Netherlands in the nineteenth century. The parade take...
- unesco_ich_id: '1708'
name: Falconry, a living human heritage
list_type: RL
list_name: Representative List of the Intangible Cultural Heritage of Humanity
inscription_year: 2021
multinational: true
url: https://ich.unesco.org/en/RL/falconry-a-living-human-heritage-01708
description: Falconry is the traditional art and practice of training and flying falcons (and sometimes eagles, hawks,
buzzards and other birds of prey). It has been practised for over 4000 years. The practice of falconry in early and
medieval periods of history is documented in many parts of the world. Original...
- unesco_ich_id: '1265'
name: Craft of the miller operating windmills and watermills
list_type: RL
list_name: Representative List of the Intangible Cultural Heritage of Humanity
inscription_year: 2017
multinational: false
url: https://ich.unesco.org/en/RL/craft-of-the-miller-operating-windmills-and-watermills-01265
description: The craft of the miller operating windmills and watermills involves the knowledge and skills necessary to
operate a mill and maintain it in a good state of repair. With a declining number of people earning their livelihood
from the craft, millers today also play a key role in transmitting the cultur...
location:
latitude: 52.3652726
longitude: 4.885896
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-11-28T09:54:38.063681+00:00'
entity_id: ChIJ__-WvekJxkcR1lmeTclWQQI
api_endpoint: https://maps.googleapis.com/maps/api/place/textsearch
city: Amsterdam
region: Noord-Holland
region_code: NH
country: NL
postal_code: 1017 GC
street_address: Kerkstraat 51-53, Amsterdam
formatted_address: Kerkstraat 51-53, 1017 GC Amsterdam
geonames_id: 2759794
geonames_name: Amsterdam
feature_code: PPLC
normalization_timestamp: '2025-12-09T07:06:10.183754+00:00'
web_person_claims:
extraction_timestamp: '2025-12-12T21:54:15.978841+00:00'
extraction_method: ch_annotator_entity_extraction_v2
filtering_applied: true
source_annotations:
- custodian/web/0593/weeshuisjes.nl/annotations_v1.7.0.yaml
persons_count: 1
persons_rejected_count: 0
persons:
- name: imke van dillen
entity_type: AGT.PER
entity_id: entity-7
class_uri: crm:E21_Person
recognition_confidence: 0.8
provenance:
xpath: /html/head/meta[4]/@content
timestamp: '2025-12-05T22:18:18.177685+00:00'
agent: zai/glm-4.6
confidence: 1.0
context_convention: GLAM-NER v1.7.0-unified
source_url: https://www.weeshuisjes.nl/
relationships: []
digital_platform_v2:
transformation_metadata:
transformed_from: httpx_beautifulsoup
transformation_date: '2025-12-14T23:59:42.817585+00:00'
transformation_version: '2.1'
source_status_code: 200
primary_platform:
platform_id: primary_website_weeshuisjes_nl
platform_name: Weeshuisjes Website
platform_url: https://www.weeshuisjes.nl/
platform_type: DISCOVERY_PORTAL
description: "WEESHUISJES HULP STAAT KLAAR\nWIL JIJ MEER SOCIAAL GELUK IN JE EIGEN LEEFOMGEVING?\nDAN STAAT STICHTING\
\ WEESHUISJES VOOR JE KLAAR.\n\nWIJ ZIJN OP ZOEK NAAR \"SOCIAL DESIGNERS\"\nEN BUURTBEWONERS DIE INITIATIEVEN HEBBEN\n\
VOOR TIJDELIJKE SOCIALE HERBESTEMMING \n V"
language: en
og_image: https://www.weeshuisjes.nl/uploads/5/0/4/8/50482345/weeshuisjes-soc-geluk-black_orig.jpg
favicon: null
collection_urls:
- https://www.weeshuisjes.nl/collectie.html
navigation_links:
- https://www.weeshuisjes.nl/
- https://www.weeshuisjes.nl/film-zwv.html
- https://www.weeshuisjes.nl/brughuisjes.html
- https://www.weeshuisjes.nl/weeshuisjes.html
- https://www.weeshuisjes.nl/weeshuisjes-den-bosch.html
- https://www.weeshuisjes.nl/opzichter-fred.html
- https://www.weeshuisjes.nl/weeshuisjes-helmond.html
- https://www.weeshuisjes.nl/thuis-van-de-liefhebber.html
- https://www.weeshuisjes.nl/t-koninklijk-nederlands-vissershuis.html
- https://www.weeshuisjes.nl/verhaal-aan-de-knaal.html
- https://www.weeshuisjes.nl/weeshuisje-den-dungen.html
- https://www.weeshuisjes.nl/huisjeopwielen.html
- https://www.weeshuisjes.nl/aanbod.html
- https://www.weeshuisjes.nl/inspiratiekit.html
- https://www.weeshuisjes.nl/boek.html
- https://www.weeshuisjes.nl/inspiratiefilmpjes.html
- https://www.weeshuisjes.nl/rondleiding.html
- https://www.weeshuisjes.nl/infoloket.html
- https://www.weeshuisjes.nl/webinar.html
- https://www.weeshuisjes.nl/collectie.html
timespan:
begin_of_the_begin: '1831-10-20T00:00:00Z'
end_of_the_begin: '1831-10-20T00:00:00Z'
begin_of_the_end: null
end_of_the_end: null
sources:
- 'Linkup web search: https://nl.wikipedia.org/wiki/Burgerweeshuis_(Kalverstraat_Amsterdam)'
notes: 'Found via pattern: full_date_nl'
web_enrichments:
extraction_timestamp: '2025-12-13T19:45:30.768112+00:00'
extraction_method: hybrid_llm_pattern_layout_v1
confidence_threshold: 0.6
entities_count: 9
claims:
- entity: Stichting Weeshuisjes
entity_type: GRP.ASS
xpath: /html/head/meta[2]/@content
base_confidence: 0.9
layout_score: 0.0
pattern_score: 0.15
final_confidence: 1.0
pattern_match: \b(vereniging|stichting|genootschap|kring)\b
- entity: https://www.weeshuisjes.nl/
entity_type: APP.URL
xpath: /html/head/meta[6]/@content
base_confidence: 1.0
layout_score: 0.0
pattern_score: 0.0
final_confidence: 1.0
- entity: helmond
entity_type: TOP.SET
xpath: /html/head/meta[4]/@content
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.15
final_confidence: 0.95
pattern_match: ^[A-Z][a-z]+$
- entity: imke van dillen
entity_type: AGT.PER
xpath: /html/head/meta[4]/@content
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.15
final_confidence: 0.95
pattern_match: ^[A-Z][a-z]+\s+[A-Z][a-z]+
- entity: BRUGHUISJES
entity_type: GRP.ASS
xpath: /html/head/meta[2]/@content
base_confidence: 0.85
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.85
- entity: den bosch
entity_type: TOP.SET
xpath: /html/head/meta[4]/@content
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: social design
entity_type: THG.CON
xpath: /html/head/meta[4]/@content
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: boek
entity_type: WRK.TXT
xpath: /html/head/meta[4]/@content
base_confidence: 0.8
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.8
- entity: Dutch
entity_type: THG.LNG
xpath: /html/@lang
base_confidence: 0.7
layout_score: 0.0
pattern_score: 0.0
final_confidence: 0.7
wikidata_id: Q55
wikidata_label: Netherlands
wikidata_linking_timestamp: '2025-12-13T23:04:19.782787'