Triple

T14290018
Position Surface form Disambiguated ID Type / Status
Subject Mary Tyler Moore E354283 entity
Predicate spouse P13 FINISHED
Object Grant Tinker E227356 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: Grant Tinker | Statement: [Mary Tyler Moore, spouse, Grant Tinker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grant Tinker
Context triple: [Mary Tyler Moore, spouse, Grant Tinker]
  • A. Grant Tinker chosen
    Grant Tinker was an influential American television executive and producer, best known as the co-founder of MTM Enterprises and former chairman and CEO of NBC.
  • B. Tony Hinkle
    Tony Hinkle was a legendary American coach and innovator in college basketball, best known for his long and influential tenure at Butler University and for helping popularize the orange basketball.
  • C. Willard Mackey
    Willard Mackey is an individual significant enough in the field of mechanical engineering to have a named professorship at Johns Hopkins University established in his honor.
  • D. Walt Willey
    Walt Willey is an American actor best known for his long-running role as attorney Jackson Montgomery on the soap opera "All My Children."
  • E. John Dye
    John Dye was an American actor best known for his role as the angel Andrew on the television series "Touched by an Angel."
  • 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_69d8278e17088190b328c5a9d4be74ff completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6981e9148190baf2ed56a7b7340e completed April 14, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d1fee448190bcafb37dd6618d60 completed May 8, 2026, 1:32 a.m.
Created at: April 10, 2026, 1:11 a.m.