bd06e4f864
Merge data from PENDING files (with XX-XXX placeholders) into their corresponding enriched custodian records with proper GHCIDs. Countries affected: - DE: 4 institutions (Deutsche Stiftung, Jewish Museum Berlin, etc.) - ES: 1 institution (Biblioteca Nacional de España) - FR: 1 institution (NMO) - ID: 18 Indonesian museums and archives - NL: 111 Dutch institutions across all provinces - US: 1 institution (ARCA) The PENDING files are deleted after merge; originals archived in data/custodian/archive/pending_merged_20250109/
117 lines
3.8 KiB
YAML
117 lines
3.8 KiB
YAML
custodian_name:
|
|
emic_name: Museum Berjalan
|
|
emic_name_source: linkedin
|
|
institution_type:
|
|
- M
|
|
linkedin_enrichment:
|
|
linkedin_url: https://www.linkedin.com/company/museum-berjalan
|
|
linkedin_slug: museum-berjalan
|
|
industry: null
|
|
website: null
|
|
follower_count: '201'
|
|
staff_count: 3
|
|
heritage_staff_count: 1
|
|
heritage_staff:
|
|
- name: Museum Berjalan
|
|
headline: ''
|
|
heritage_type: M
|
|
enrichment_timestamp: '2025-12-16T21:06:37.271459+00:00'
|
|
provenance:
|
|
source: linkedin_company_scrape
|
|
original_file: data/custodian/linkedin/museum-berjalan.yaml
|
|
schema_version: 1.0.0
|
|
location:
|
|
city: Depok
|
|
region: JB
|
|
country: ID
|
|
ghcid:
|
|
ghcid_current: ID-JB-DEP-M-MB
|
|
ghcid_original: NL-XX-XXX-M-MB
|
|
ghcid_uuid: d32a6812-b6b3-574d-8ae5-8c9a2c867fbb
|
|
ghcid_uuid_sha256: bebc6235-2f20-8d30-a854-d666714ead83
|
|
ghcid_numeric: 18026884144120781497
|
|
record_id: a1772d44-6ca0-4120-8a24-71b3fb9992a1
|
|
generation_timestamp: '2025-12-17T08:14:12.983501+00:00'
|
|
ghcid_history:
|
|
- ghcid: ID-JB-DEP-M-MB
|
|
ghcid_numeric: 18026884144120781497
|
|
valid_from: '2025-12-17T08:14:12.983501+00:00'
|
|
valid_to: null
|
|
reason: Corrected country from NL to ID based on city location (Depok)
|
|
- ghcid: NL-XX-XXX-M-MB
|
|
ghcid_numeric: 13743968143391386928
|
|
valid_from: '2025-12-16T21:06:37.271459+00:00'
|
|
valid_to: '2025-12-17T08:14:12.983501+00:00'
|
|
reason: Initial GHCID assignment from LinkedIn batch import
|
|
location_resolution:
|
|
method: CITY_LOOKUP
|
|
city_code: DEP
|
|
city_name: Depok
|
|
region_code: JB
|
|
country_code: ID
|
|
resolution_date: '2025-12-17T08:14:12.983501+00:00'
|
|
provenance:
|
|
schema_version: 2.0.0
|
|
generated_at: '2025-12-28T20:01:08.165567+00:00'
|
|
sources:
|
|
linkedin:
|
|
- source_type: linkedin_company_profile
|
|
data_tier: TIER_4_INFERRED
|
|
source_file: data/custodian/linkedin/museum-berjalan.yaml
|
|
extraction_timestamp: '2025-12-16T21:06:37.271459+00:00'
|
|
claims_extracted:
|
|
- name
|
|
- industry
|
|
- location
|
|
- website
|
|
- staff_count
|
|
- heritage_staff
|
|
data_tier_summary:
|
|
TIER_4_INFERRED:
|
|
- linkedin_company_profile
|
|
notes:
|
|
- Created from unmatched LinkedIn company profile
|
|
- 'Location resolution method: UNRESOLVED'
|
|
- Staff data merged from NL-XX-XXX-PENDING-MUSEUM-BERJALAN.yaml on 2026-01-09T15:45:37.064190+00:00
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-++XVhaSpDnt5W3v5rDYAYg1ckyoDH6dIThS8MwNJ76w=
|
|
verified_at: '2025-12-28T20:01:08.165555+00:00'
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
wikidata_enrichment:
|
|
wikidata_id: null
|
|
enrichment_timestamp: '2025-12-21T00:00:00Z'
|
|
enrichment_method: manual_wikidata_lookup
|
|
enrichment_note: No Wikidata entry found for Museum Berjalan
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-++XVhaSpDnt5W3v5rDYAYg1ckyoDH6dIThS8MwNJ76w=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T20:01:08.165555+00:00'
|
|
prov:
|
|
wasGeneratedBy:
|
|
'@type': prov:Activity
|
|
name: wikidata_api_fetch
|
|
used: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T20:01:08.165560+00:00'
|
|
staff:
|
|
provenance:
|
|
source_type: linkedin_company_people_page_html
|
|
registered_timestamp: '2025-12-30T09:55:30Z'
|
|
registration_method: html_parsing_with_full_staff_data
|
|
total_staff_extracted: 1
|
|
staff_list:
|
|
- staff_id: museum-berjalan_staff_0002_trisno_juliantoro
|
|
person_name: Trisno Juliantoro
|
|
person_profile_path: data/custodian/person/entity/trisno-juliantoro_*.json
|
|
role_title: Communication & Media Enthusiast. Media Consultant at INDIGITAL
|
|
heritage_relevant: false
|
|
heritage_type: null
|
|
linkedin_profile_url: https://www.linkedin.com/in/trisno-juliantoro
|
|
linkedin_slug: trisno-juliantoro
|