Triple

T10456132
Position Surface form Disambiguated ID Type / Status
Subject Forman E246554 entity
Predicate hasAlternativeSpelling P457 FINISHED
Object Furman E135514 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: Furman | Statement: [Forman, hasAlternativeSpelling, Furman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Furman
Context triple: [Forman, hasAlternativeSpelling, Furman]
  • A. Furman University chosen
    Furman University is a private liberal arts university known for its rigorous academics and picturesque campus in Greenville, South Carolina.
  • B. Wofford
    Wofford is the birth surname of Nobel Prize–winning American novelist Toni Morrison.
  • C. Wake Forest
    Wake Forest is a town in North Carolina that forms part of the greater Research Triangle region anchored by Raleigh, Durham, and Chapel Hill.
  • D. University of South Carolina
    The University of South Carolina is a major public research university in Columbia, South Carolina, known for its comprehensive academic programs and prominent NCAA Division I athletics.
  • E. Clemson University
    Clemson University is a major public research university in Clemson, South Carolina, known for its strong engineering and science programs and prominent NCAA Division I athletic teams.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe48d15c8190bae0d4859e6cda5d completed April 7, 2026, 12:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69d87f10b45c81908f1d3128c65750f8 completed April 10, 2026, 4:39 a.m.
Created at: April 6, 2026, 12:18 p.m.