Triple

T20884277
Position Surface form Disambiguated ID Type / Status
Subject Univ E514233 entity
Predicate shortName P43 FINISHED
Object Univ NE NERFINISHED

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: Univ | Statement: [Univ, shortName, Univ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Univ
Context triple: [Univ, shortName, Univ]
  • A. Univ chosen
    Univ is the informal abbreviation for University College, one of the constituent colleges of the University of Oxford.
  • B. Universitet
    Universitet is a Moscow Metro station serving the area around the Moscow State University campus on the Lenin Hills.
  • C. Universitate
    Universitate is a central Bucharest metro station located near the University of Bucharest and several major cultural and administrative landmarks.
  • D. Universitas
    Universitas is a Latin term commonly used to denote a university or community of scholars dedicated to higher learning and research.
  • E. Universidad
    Universidad is a Mexico City Metro station that serves as a major southern terminus and gateway to the National Autonomous University of Mexico (UNAM) campus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67bd32c819097301e330e358c49 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:46 p.m.