Triple

T10169483
Position Surface form Disambiguated ID Type / Status
Subject Geoff Collins E235292 entity
Predicate name P16 FINISHED
Object Geoff Collins E235292 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: Geoff Collins | Statement: [Geoff Collins, name, Geoff Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geoff Collins
Context triple: [Geoff Collins, name, Geoff Collins]
  • A. Geoff Collins chosen
    Geoff Collins is an American football coach best known for his head coaching stints at Temple University and Georgia Tech, as well as his defensive coaching roles at several major college programs.
  • B. Paul Collins
    Paul Collins is a voice actor best known for providing the voice of Peter Pan in animated adaptations.
  • C. Geoff Pierson
    Geoff Pierson is an American actor known for his work in television dramas and comedies, including prominent roles on shows like Dexter and Unhappily Ever After.
  • D. Geoff Hall
    Geoff Hall is a cinematographer known for his work on the Australian film "Red Dog."
  • E. Steve Collins
    Steve Collins is a fictional character appearing in the classic 1941 screwball comedy film "The Bride Came C.O.D."
  • 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_69ca84ceafd0819085828600e11bed6b completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdec9ba56481908b5265aea8ea8cbe completed April 2, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d74fce236481909387829c7cf311a4 completed April 9, 2026, 7:05 a.m.
Created at: March 30, 2026, 9:10 p.m.