224 lines
8.7 KiB
YAML
224 lines
8.7 KiB
YAML
original_entry:
|
|
name: Internet Archive
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Website
|
|
identifier_value: https://archive.org/
|
|
identifier_url: https://archive.org/
|
|
- identifier_scheme: GHCID
|
|
identifier_value: US-CA-SAN-A-IA
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '213324328442227739'
|
|
- &id002
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: https://w3id.org/heritage/custodian/mx/a-internet-archive-0113
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: a0cc444e-9393-5f88-8cbf-7e63ac831249
|
|
identifier_url: urn:uuid:a0cc444e-9393-5f88-8cbf-7e63ac831249
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 02f5e158-b2bf-8c1b-a302-cf050a43c559
|
|
identifier_url: urn:uuid:02f5e158-b2bf-8c1b-a302-cf050a43c559
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 019a58fd-3229-7e09-8740-57e413f04639
|
|
identifier_url: urn:uuid:019a58fd-3229-7e09-8740-57e413f04639
|
|
- &id003
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: 213324328442227739
|
|
locations:
|
|
- city: San Francisco
|
|
region: California
|
|
country: US
|
|
processing_timestamp: '2025-12-06T23:39:02.326629+00:00'
|
|
ghcid:
|
|
ghcid_current: US-CA-SAN-A-IA
|
|
ghcid_original: US-CA-SAN-A-IA
|
|
ghcid_uuid: a0cc444e-9393-5f88-8cbf-7e63ac831249
|
|
ghcid_uuid_sha256: 02f5e158-b2bf-8c1b-2302-cf050a43c559
|
|
ghcid_numeric: 213324328442227739
|
|
record_id: d80a9256-d0ff-454f-8aa6-0ba5d905845b
|
|
generation_timestamp: '2025-12-06T23:39:02.326629+00:00'
|
|
location_resolution:
|
|
country_code: US
|
|
region_code: CA
|
|
city_code: SAN
|
|
method: CH_ANNOTATOR_SOURCE
|
|
ghcid_history:
|
|
- ghcid: US-CA-SAN-A-IA
|
|
ghcid_numeric: 213324328442227739
|
|
valid_from: '2025-12-06T23:39:02.326629+00:00'
|
|
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Internet Archive
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: US-CA-SAN-A-IA
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: a0cc444e-9393-5f88-8cbf-7e63ac831249
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 02f5e158-b2bf-8c1b-2302-cf050a43c559
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '213324328442227739'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: d80a9256-d0ff-454f-8aa6-0ba5d905845b
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
provenance:
|
|
data_source: CONVERSATION_NLP
|
|
data_tier: TIER_4_INFERRED
|
|
extraction_date: '2025-11-06T07:54:59.620774+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
|
|
confidence_score: 0.85
|
|
notes:
|
|
- 'YouTube/Google Maps enrichment 2025-12-08T19:41:06Z: Maps: rejected by LLM; YouTube: not found'
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T07:13:45Z
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-iJpCINJzNww4NgO+W0v2vKj7/ydvX2ZIRGM+PIQpaMo=
|
|
verified_at: '2025-12-28T20:09:38.052242+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q461
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T20:09:38.052259+00:00'
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.HER.ARC
|
|
subtype_label: ARCHIVE
|
|
ontology_class: schema:ArchiveOrganization
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /conversations/mixed
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-06T07:54:59.620774+00:00'
|
|
statement_created_at: '2025-12-30T21:23:27.936301+00:00'
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30 (ch_annotator.extraction_provenance)
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:13:56.173868+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: latin_american_institutions_AUTHORITATIVE.yaml
|
|
annotation_metadata:
|
|
confidence_score: 0.85
|
|
verified: false
|
|
verification_date: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Internet Archive
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/mixed
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-06T07:54:59.620774+00:00'
|
|
statement_created_at: '2025-12-30T21:23:27.936311+00:00'
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30 (entity_claims[0].provenance)
|
|
confidence: 0.85
|
|
- claim_type: institution_type
|
|
claim_value: ARCHIVE
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/mixed
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-06T07:54:59.620774+00:00'
|
|
statement_created_at: '2025-12-30T21:23:27.936314+00:00'
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30 (entity_claims[1].provenance)
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: San Francisco
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/mixed
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-06T07:54:59.620774+00:00'
|
|
statement_created_at: '2025-12-30T21:23:27.936316+00:00'
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30 (entity_claims[2].provenance)
|
|
confidence: 0.9
|
|
- claim_type: ghcid
|
|
claim_value: US-CA-SAN-A-IA
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/mixed
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-06T07:54:59.620774+00:00'
|
|
statement_created_at: '2025-12-30T21:23:27.936317+00:00'
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30 (entity_claims[3].provenance)
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:39:02.326629+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_status: NO_MATCH
|
|
google_maps_rejected:
|
|
candidate_name: Internet Archive Europe
|
|
rejection_reason: Rejected due to location mismatch. The source institution is in the US, while the candidate is in the
|
|
Netherlands. Although the names are related, indicating a branch of the parent institution, the location is in a different
|
|
country. The Google Place type 'point_of_interest' is also not specific enough to confirm the entity type.
|
|
timestamp: '2025-12-08T19:41:05.807957+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Internet Archive official
|
|
youtube_search_timestamp: '2025-12-08T19:41:06.153916+00:00'
|
|
location:
|
|
city: San Francisco
|
|
region: California
|
|
region_code: CA
|
|
country: US
|
|
normalization_timestamp: '2025-12-09T19:32:31.442626+00:00'
|
|
latitude: 37.77493
|
|
longitude: -122.41942
|
|
coordinate_provenance:
|
|
source_type: GEONAMES_LOCAL
|
|
source_path: data/reference/geonames.db
|
|
entity_id: 5391959
|
|
original_timestamp: '2025-12-09T19:32:31.441756+00:00'
|
|
geonames_id: 5391959
|
|
geonames_name: San Francisco
|
|
feature_code: PPLA2
|
|
wikidata_enrichment:
|
|
wikidata_id: Q461
|
|
wikidata_label: Internet Archive
|
|
wikidata_description: American non-profit organization
|
|
wikidata_url: https://www.wikidata.org/wiki/Q461
|
|
enrichment_timestamp: '2025-01-21T00:00:00Z'
|
|
enrichment_method: manual_wikidata_lookup
|
|
enrichment_note: Major digital archive and web preservation organization based in San Francisco
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-iJpCINJzNww4NgO+W0v2vKj7/ydvX2ZIRGM+PIQpaMo=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T20:09:38.052242+00:00'
|
|
prov:
|
|
wasGeneratedBy:
|
|
'@type': prov:Activity
|
|
name: wikidata_api_fetch
|
|
used: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q461
|
|
generatedAtTime: '2025-01-21T00:00:00Z'
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T20:09:38.052250+00:00'
|
|
wikidata_entity_id: Q461
|