Triple

T11999377
Position Surface form Disambiguated ID Type / Status
Subject Elyse Knox E285616 entity
Predicate spouse P13 FINISHED
Object Tom Harmon E277823 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: Tom Harmon | Statement: [Elyse Knox, spouse, Tom Harmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Harmon
Context triple: [Elyse Knox, spouse, Tom Harmon]
  • A. Tom Harmon chosen
    Tom Harmon was a celebrated American football player and Heisman Trophy–winning halfback who later became a sports broadcaster and actor.
  • B. Bronko Nagurski
    Bronko Nagurski was a legendary Hall of Fame fullback and defensive tackle for the Chicago Bears, renowned for his power running and dominance in the early years of the NFL.
  • C. Ernie Davis
    Ernie Davis was a trailblazing American college football running back who became the first African American to win the Heisman Trophy and a symbol of progress in sports during the civil rights era.
  • D. Gale Sayers
    Gale Sayers was a Hall of Fame NFL running back for the Chicago Bears, renowned for his electrifying speed and elusive running style during the 1960s.
  • E. Tommy Nobis
    Tommy Nobis was a dominant All-Pro linebacker for the Atlanta Falcons and a cornerstone of their early franchise history.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903c26d7881909b67a31d04882eb5 completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f472917ed08190a872d9e5663d5ed5 completed May 1, 2026, 9:29 a.m.
Created at: April 8, 2026, 9:46 p.m.