Triple

T19267934
Position Surface form Disambiguated ID Type / Status
Subject Cindy Gruden E481837 entity
Predicate spouse P13 FINISHED
Object Jon Gruden 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: Jon Gruden | Statement: [Cindy Gruden, spouse, Jon Gruden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jon Gruden
Context triple: [Cindy Gruden, spouse, Jon Gruden]
  • A. Jon Gruden chosen
    Jon Gruden is an American football coach and former broadcaster best known for leading the Tampa Bay Buccaneers to a Super Bowl title and later serving as head coach of the Oakland/Las Vegas Raiders.
  • B. Sherry Gruden
    Sherry Gruden is best known as the wife of American football coach Jay Gruden and a longtime supportive presence throughout his coaching career.
  • C. Jim Gruden
    Jim Gruden is the patriarch of the Gruden football family and father of NFL coaches Jon and Jay Gruden.
  • D. Jay Gruden
    Jay Gruden is an American football coach and former quarterback best known for his success in the Arena Football League and for serving as head coach of the NFL’s Washington Redskins.
  • E. Brad Johnson
    Brad Johnson was an American actor best known for his roles in films like "Always" and "Flight of the Intruder" and the TV series "Melrose Place."
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8e1f888190a95f60fa29ca3b98 completed April 20, 2026, 10:10 a.m.
Created at: April 10, 2026, 1:29 p.m.