e5a532a8bc
- Introduced `test_nlp_extractor.py` with unit tests for the InstitutionExtractor, covering various extraction patterns (ISIL, Wikidata, VIAF, city names) and ensuring proper classification of institutions (museum, library, archive). - Added tests for extracted entities and result handling to validate the extraction process. - Created `test_partnership_rdf_integration.py` to validate the end-to-end process of extracting partnerships from a conversation and exporting them to RDF format. - Implemented tests for temporal properties in partnerships and ensured compliance with W3C Organization Ontology patterns. - Verified that extracted partnerships are correctly linked with PROV-O provenance metadata.
86 lines
2.4 KiB
JSON
86 lines
2.4 KiB
JSON
[
|
|
{
|
|
"id": "rijksmuseum-amsterdam",
|
|
"name": "Rijksmuseum",
|
|
"alternative_names": [],
|
|
"institution_type": "MUSEUM",
|
|
"organization_status": "ACTIVE",
|
|
"description": "Dutch national museum in Amsterdam with over 1 million objects",
|
|
"identifiers": [
|
|
{
|
|
"identifier_scheme": "ISIL",
|
|
"identifier_value": "NL-AsdRM"
|
|
}
|
|
],
|
|
"locations": [
|
|
{
|
|
"street_address": "Museumstraat 1",
|
|
"city": "Amsterdam",
|
|
"postal_code": "1071 XX",
|
|
"country": "NL",
|
|
"is_primary": true
|
|
}
|
|
],
|
|
"homepage": "https://www.rijksmuseum.nl/en/rijksstudio",
|
|
"metadata_standards": ["SPECTRUM", "LIDO"],
|
|
"collections": [
|
|
{
|
|
"collection_description": "Over 1 million objects including masterpieces by Rembrandt and Vermeer",
|
|
"item_count": 1000000
|
|
}
|
|
],
|
|
"partnerships": [
|
|
{
|
|
"partner_name": "Museumvereniging",
|
|
"partnership_type": "membership"
|
|
}
|
|
],
|
|
"provenance": {
|
|
"data_source": "CONVERSATION_NLP",
|
|
"data_tier": "TIER_4_INFERRED",
|
|
"extraction_method": "NER + pattern matching",
|
|
"confidence_score": 0.95,
|
|
"conversation_id": "test-uuid-001"
|
|
}
|
|
},
|
|
{
|
|
"id": "nationaal-archief-den-haag",
|
|
"name": "Nationaal Archief",
|
|
"alternative_names": ["National Archive"],
|
|
"institution_type": "ARCHIVE",
|
|
"organization_status": "ACTIVE",
|
|
"description": "National Archive of the Netherlands with documents dating back to the 9th century",
|
|
"identifiers": [
|
|
{
|
|
"identifier_scheme": "ISIL",
|
|
"identifier_value": "NL-HaNA"
|
|
}
|
|
],
|
|
"locations": [
|
|
{
|
|
"street_address": "Prins Willem-Alexanderhof 20",
|
|
"city": "Den Haag",
|
|
"postal_code": "2595 BE",
|
|
"country": "NL",
|
|
"is_primary": true
|
|
}
|
|
],
|
|
"homepage": "https://www.nationaalarchief.nl",
|
|
"metadata_standards": ["EAD", "RIC_O"],
|
|
"parent_organization": "Ministry of Education, Culture and Science",
|
|
"partnerships": [
|
|
{
|
|
"partner_name": "Network of Regional Archives",
|
|
"partner_id": "Netwerk Archieven",
|
|
"partnership_type": "network_membership"
|
|
}
|
|
],
|
|
"provenance": {
|
|
"data_source": "CONVERSATION_NLP",
|
|
"data_tier": "TIER_4_INFERRED",
|
|
"extraction_method": "NER + pattern matching",
|
|
"confidence_score": 0.93,
|
|
"conversation_id": "test-uuid-001"
|
|
}
|
|
}
|
|
]
|