Triple

T7415214
Position Surface form Disambiguated ID Type / Status
Subject ORCID E171110 entity
Predicate hasAPI P182 FINISHED
Object ORCID Public API E171110 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: ORCID Public API | Statement: [ORCID, hasAPI, ORCID Public API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ORCID Public API
Context triple: [ORCID, hasAPI, ORCID Public API]
  • A. ORCID chosen
    ORCID is a non-profit organization that provides unique, persistent digital identifiers to researchers, enabling accurate attribution of their scholarly work across systems and platforms.
  • B. Publons
    Publons is an online platform that helps researchers track, verify, and showcase their peer review and editorial contributions for academic journals.
  • C. Microsoft Academic Search
    Microsoft Academic Search was a free academic search engine and research tool developed by Microsoft that indexed scholarly publications and provided citation analysis and visualization features.
  • D. DBLP
    DBLP is a comprehensive computer science bibliography database that indexes research papers, conference proceedings, and journals in the field of computing.
  • E. ISNI database
    The ISNI database is a global registry that assigns and maintains unique identifiers for public identities such as authors, researchers, and organizations to ensure accurate attribution and disambiguation.
  • 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_69c68a618bdc81908d8018edadecd1a4 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2c643248190a387abba2f482b25 completed March 27, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ee1b48c81909912ff0d7bf2837e completed March 28, 2026, 6:33 p.m.
Created at: March 27, 2026, 3:11 p.m.