Triple

T6175512
Position Surface form Disambiguated ID Type / Status
Subject Harvard Dataverse E137807 entity
Predicate supportsStandard P1587 FINISHED
Object Dublin Core metadata E166787 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Dublin Core metadata | Statement: [Harvard Dataverse, supportsStandard, Dublin Core metadata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dublin Core metadata
Context triple: [Harvard Dataverse, supportsStandard, Dublin Core metadata]
  • A. Dublin Core chosen
    Dublin Core is a widely used standard for describing digital resources through a simple, generic set of metadata elements to support discovery and interoperability across systems.
  • B. S-100 metadata framework
    The S-100 metadata framework is an IHO-developed standard that defines a flexible, interoperable structure for describing and managing geospatial and hydrographic data within the broader S-100 universal hydrographic data model.
  • C. METS
    METS (Metadata Encoding and Transmission Standard) is an XML-based standard for encoding descriptive, administrative, and structural metadata for complex digital library objects.
  • D. BIBFRAME
    BIBFRAME (Bibliographic Framework) is a linked data model and standard developed by the Library of Congress to replace MARC for describing and sharing bibliographic information on the web.
  • E. Library of Congress Linked Data Service
    The Library of Congress Linked Data Service is an online platform that publishes the Library of Congress’s controlled vocabularies and authority data in machine-readable linked data formats for use in cataloging and semantic web applications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05dc70ac481909fd1db0d69837eca completed March 22, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141b69c348190a4e530b7380b643f completed March 23, 2026, 1:35 p.m.
Created at: March 22, 2026, 4:18 p.m.