262 lines
9.8 KiB
YAML
262 lines
9.8 KiB
YAML
original_entry:
|
|
name: Hemeroteca Digital
|
|
institution_type: MIXED
|
|
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-TO-XXX-M-HD
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '11520985515572423252'
|
|
- &id001
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: https://w3id.org/heritage/custodian/br/hemeroteca-digital
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 16fe1165-834d-5ec0-94dc-5d6d190cb29e
|
|
identifier_url: urn:uuid:16fe1165-834d-5ec0-94dc-5d6d190cb29e
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 9fe2c349-1e1d-8a54-acc0-8204b96154b8
|
|
identifier_url: urn:uuid:9fe2c349-1e1d-8a54-acc0-8204b96154b8
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 019a58fd-3227-783f-8dd7-d7d65ace2325
|
|
identifier_url: urn:uuid:019a58fd-3227-783f-8dd7-d7d65ace2325
|
|
- &id002
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: 11520985515572423252
|
|
locations:
|
|
- country: BR
|
|
region: TOCANTINS
|
|
processing_timestamp: '2025-12-06T23:39:01.777539+00:00'
|
|
ghcid:
|
|
ghcid_current: BR-RJ-CEN-X-HD-hemeroteca_digital
|
|
ghcid_original: BR-TO-XXX-X-HD-hemeroteca_digital
|
|
ghcid_uuid: acb30794-3c8e-5026-bbb1-ef4ccaaa3a9c
|
|
ghcid_uuid_sha256: 931c02a5-7b95-8f4f-36e4-f52b1b77d562
|
|
ghcid_numeric: 10600350532689567567
|
|
record_id: 4851a7ba-74a4-4693-8a1a-a2626ce680f5
|
|
generation_timestamp: '2025-12-06T23:39:01.777539+00:00'
|
|
location_resolution:
|
|
method: GOOGLE_PLACES_GEONAMES
|
|
country_code: BR
|
|
region_code: RJ
|
|
region_name: Rio de Janeiro
|
|
city_code: CEN
|
|
city_name: Centro
|
|
geonames_id: 8534637
|
|
feature_code: PPL
|
|
google_place_id: ChIJ0QTJyWF_mQAR4t3oNko2kQo
|
|
latitude: -22.9096965
|
|
longitude: -43.1755177
|
|
resolution_date: '2025-12-07T16:39:18.685576+00:00'
|
|
ghcid_history:
|
|
- ghcid: BR-TO-XXX-X-HD-hemeroteca_digital
|
|
ghcid_numeric: 10600350532689567567
|
|
valid_from: '2025-12-06T23:39:01.777539+00:00'
|
|
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
valid_to: '2025-12-07T16:39:18.685576+00:00'
|
|
- ghcid: BR-RJ-CEN-X-HD-hemeroteca_digital
|
|
ghcid_numeric: 10600350532689567567
|
|
valid_from: '2025-12-07T16:39:18.685576+00:00'
|
|
reason: 'Location resolved via Google Places + GeoNames: Centro (RJ)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Hemeroteca Digital
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-RJ-CEN-X-HD-hemeroteca_digital
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: acb30794-3c8e-5026-bbb1-ef4ccaaa3a9c
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 931c02a5-7b95-8f4f-36e4-f52b1b77d562
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '10600350532689567567'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 4851a7ba-74a4-4693-8a1a-a2626ce680f5
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: CONVERSATION_NLP
|
|
data_tier: TIER_4_INFERRED
|
|
extraction_date: '2025-11-06T08:25:13.555433+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
|
|
confidence_score: 0.7
|
|
notes:
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:10:53Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:46:57Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:48:22Z
|
|
- 'YouTube/Google Maps enrichment 2025-12-09T08:51:47Z: YouTube: not found'
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-5TAKu10D986Jmea5lPlWJ3UEhdS+0V+4eBdd91OMq8M=
|
|
verified_at: '2025-12-28T19:57:36.943751+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q948882
|
|
google_maps_enrichment:
|
|
content_hash: sha256-kiSVxIE1BPf3FR4yMFHe3jFAzMdTIjDNgb6tBtx/jLs=
|
|
verified_at: '2025-12-28T19:57:36.943784+00:00'
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T19:57:36.943795+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.MIX
|
|
subtype_label: MIXED
|
|
ontology_class: glam:HeritageCustodian
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555433+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
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: 0.7
|
|
verified: false
|
|
verification_date:
|
|
verified_by:
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Hemeroteca Digital
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555433+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.7
|
|
- claim_type: institution_type
|
|
claim_value: MIXED
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555433+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: ghcid
|
|
claim_value: BR-TO-XXX-M-HD
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555433+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:39:01.777539+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_enrichment:
|
|
place_id: ChIJ0QTJyWF_mQAR4t3oNko2kQo
|
|
formatted_address: Av. Rio Branco, 219 - Centro, Rio de Janeiro - RJ, 20040-008, Brazil
|
|
website: https://www.gov.br/bn/pt-br
|
|
latitude: -22.9096965
|
|
longitude: -43.1755177
|
|
enriched_at: '2025-12-07T16:39:18.685576+00:00'
|
|
source: Google Places API (New)
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-kiSVxIE1BPf3FR4yMFHe3jFAzMdTIjDNgb6tBtx/jLs=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:57:36.943784+00:00'
|
|
prov:
|
|
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJ0QTJyWF_mQAR4t3oNko2kQo
|
|
wasGeneratedBy:
|
|
'@type': prov:Activity
|
|
name: google_maps_api_fetch
|
|
used: https://maps.googleapis.com/maps/api/place
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:57:36.943787+00:00'
|
|
location:
|
|
latitude: -22.9096965
|
|
longitude: -43.1755177
|
|
coordinate_provenance:
|
|
source_type: GHCID_RESOLUTION_DIRECT
|
|
source_path: ghcid.location_resolution
|
|
entity_id: 8534637
|
|
resolution_method: GOOGLE_PLACES_GEONAMES
|
|
city: Centro
|
|
region: Rio de Janeiro
|
|
region_code: RJ
|
|
country: BR
|
|
formatted_address: Av. Rio Branco, 219 - Centro, Rio de Janeiro - RJ, 20040-008, Brazil
|
|
geonames_id: 8534637
|
|
feature_code: PPL
|
|
normalization_timestamp: '2025-12-09T06:48:22.619384+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Hemeroteca Digital official
|
|
youtube_search_timestamp: '2025-12-09T08:51:47.737274+00:00'
|
|
wikidata_enrichment:
|
|
wikidata_id: Q948882
|
|
wikidata_url: https://www.wikidata.org/wiki/Q948882
|
|
label: National Library of Brazil
|
|
description: Brazilian national library
|
|
enrichment_timestamp: '2025-01-13T00:00:00Z'
|
|
enrichment_method: manual_wikidata_lookup
|
|
identifiers:
|
|
VIAF: '133262876'
|
|
GND: 1003296-4
|
|
LCNAF: n50052724
|
|
official_website: https://gov.br/bn
|
|
notes: Hemeroteca Digital is a digital newspaper archive project of the National Library of Brazil
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-5TAKu10D986Jmea5lPlWJ3UEhdS+0V+4eBdd91OMq8M=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:57:36.943751+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/Q948882
|
|
generatedAtTime: '2025-01-13T00:00:00Z'
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:57:36.943765+00:00'
|
|
wikidata_entity_id: Q948882
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-22T14:42:36.170235+00:00'
|
|
source_url: https://www.gov.br/bn/pt-br
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: favicon_url
|
|
claim_value: https://www.gov.br/bn/++theme++padrao_govbr/favicons/safari-pinned-tab.svg
|
|
source_url: https://www.gov.br/bn/pt-br
|
|
css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(19)'
|
|
retrieved_on: '2025-12-22T14:42:36.170235+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: ''
|
|
favicon_sizes: ''
|
|
- claim_type: og_image_url
|
|
claim_value: https://www.gov.br/bn/pt-br/pagina-inicial/@@images/a77ea548-c4fd-4178-94e6-ffb1ca712ae9.jpeg
|
|
source_url: https://www.gov.br/bn/pt-br
|
|
css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(7)'
|
|
retrieved_on: '2025-12-22T14:42:36.170235+00:00'
|
|
extraction_method: crawl4ai_meta_og
|
|
summary:
|
|
total_claims: 2
|
|
has_primary_logo: false
|
|
has_favicon: true
|
|
has_og_image: true
|
|
favicon_count: 4
|