Triple

T10155136
Position Surface form Disambiguated ID Type / Status
Subject Fran Tarkenton E232756 entity
Predicate familyName P18 FINISHED
Object Tarkenton E232756 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: Tarkenton | Statement: [Fran Tarkenton, familyName, Tarkenton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarkenton
Context triple: [Fran Tarkenton, familyName, Tarkenton]
  • A. Fran Tarkenton chosen
    Fran Tarkenton is a Hall of Fame NFL quarterback best known for his scrambling style and record-setting career primarily with the Minnesota Vikings.
  • B. Terry Grossman
    Terry Grossman is a television producer best known for his work on the sitcom "The Golden Palace," a spin-off of "The Golden Girls."
  • C. Terry Grossman
    Terry Grossman is an American physician and longevity expert known for his work in anti-aging medicine and co-authoring books on life extension with futurist Ray Kurzweil.
  • D. Randall Cunningham
    Randall Cunningham is a former NFL quarterback, primarily for the Philadelphia Eagles and Minnesota Vikings, renowned for his dual-threat ability as both a passer and an exceptional runner.
  • E. Tom Owens
    Tom Owens is a former professional basketball player best known for his time in the ABA and NBA during the 1970s and early 1980s.
  • 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_69ca84885e48819088a31b127cf44904 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec38f594819088a7eb73fc25feff completed April 2, 2026, 4:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d300a40638819082e575d957711377 completed April 6, 2026, 12:39 a.m.
Created at: March 30, 2026, 9:08 p.m.