Triple

T21986232
Position Surface form Disambiguated ID Type / Status
Subject Kit Hughes E542967 entity
Predicate employer P7 FINISHED
Object College of the Holy Cross 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: College of the Holy Cross | Statement: [Kit Hughes, employer, College of the Holy Cross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: College of the Holy Cross
Context triple: [Kit Hughes, employer, College of the Holy Cross]
  • A. College of the Holy Cross chosen
    The College of the Holy Cross is a private Jesuit liberal arts college in Worcester, Massachusetts, known for its rigorous academics and strong undergraduate focus.
  • B. Holycross
    Holycross is a historic village in County Tipperary, Ireland, best known for its medieval Cistercian abbey and religious heritage.
  • C. Curry College
    Curry College is a private liberal arts institution of higher education located in Milton, Massachusetts.
  • D. Williams College
    Williams College is a highly selective private liberal arts college in Williamstown, Massachusetts, known for its strong undergraduate focus and small, residential campus.
  • E. Assumption College
    Assumption College was a Catholic liberal arts institution in Worcester, Massachusetts, that evolved into Assumption University.
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12709cb288190a2620e337fea364c completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:04 p.m.