Triple

T18368388
Position Surface form Disambiguated ID Type / Status
Subject Brian Billick E440111 entity
Predicate familyName P18 FINISHED
Object Billick 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: Billick | Statement: [Brian Billick, familyName, Billick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Billick
Context triple: [Brian Billick, familyName, Billick]
  • A. Billick chosen
    Billick is a surname most notably associated with Brian Billick, the former NFL head coach who led the Baltimore Ravens to a Super Bowl XXXV victory.
  • B. Dilfer
    Dilfer is the surname of former NFL quarterback and Super Bowl champion Trent Dilfer.
  • C. Bettis
    Bettis is a surname most prominently associated with former NFL running back and Pro Football Hall of Famer Jerome Bettis.
  • D. Cowherd
    Cowherd is a surname most prominently associated with American sports media personality and radio host Colin Cowherd.
  • E. Evan McCauley
    Evan McCauley is the protagonist of the science fiction film "Infinite," a man who discovers he has memories and skills from multiple past lives.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e51750d3dc8190b153046c1171ee2b completed April 19, 2026, 5:56 p.m.
Created at: April 10, 2026, 10:38 a.m.