Triple

T14040617
Position Surface form Disambiguated ID Type / Status
Subject Kiya Tomlin E337834 entity
Predicate hasFamilyName P18 FINISHED
Object Tomlin E67264 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: Tomlin | Statement: [Kiya Tomlin, hasFamilyName, Tomlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tomlin
Context triple: [Kiya Tomlin, hasFamilyName, Tomlin]
  • A. Trestman
    Trestman is the surname of Marc Trestman, an American football coach known for his work in the NFL and CFL.
  • B. Rhule
    Rhule is the surname of American football coach Matt Rhule, known for his collegiate and NFL head coaching roles.
  • C. Mike Tomlin chosen
    Mike Tomlin is a Super Bowl–winning head coach in the NFL, best known for his long, successful tenure leading the Pittsburgh Steelers.
  • D. Stephen Belichick
    Stephen Belichick is an American football coach, best known as an assistant on the New England Patriots staff and the son of longtime head coach Bill Belichick.
  • E. Brian Belichick
    Brian Belichick is an American football coach who has served on the New England Patriots’ staff, continuing the Belichick family’s long association with the NFL.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de311814e48190adb637e1c97c0658 completed April 14, 2026, 12:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb65a21088190a14808d09b2b9f42 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:20 p.m.