Triple

T20906202
Position Surface form Disambiguated ID Type / Status
Subject John Cullum E514804 entity
Predicate familyName P18 FINISHED
Object Cullum 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: Cullum | Statement: [John Cullum, familyName, Cullum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cullum
Context triple: [John Cullum, familyName, Cullum]
  • A. Cullum chosen
    Cullum is a surname most notably associated with George Washington Cullum, a 19th-century American military engineer and superintendent of the United States Military Academy at West Point.
  • B. McCauley
    McCauley is the maiden surname of Rosa Parks, the prominent American civil rights activist known for her pivotal role in the Montgomery bus boycott.
  • C. Hollomon
    Hollomon is a surname of English origin borne by various notable individuals in fields such as science, academia, and public service.
  • D. Ridgway
    Ridgway is a small town in southwestern Colorado known as a gateway to the San Juan Mountains and nearby outdoor recreation areas.
  • E. McCallum
    McCallum is the namesake of the McCallum Graduate School of Business, likely a notable benefactor or figure associated with the institution.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e9001a8c81909fa1004b5977d04f completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.