Triple

T15390802
Position Surface form Disambiguated ID Type / Status
Subject Amy Dubanowski E368037 entity
Predicate coworker P398 FINISHED
Object Glenn Sturgis E1208944 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: Glenn Sturgis | Statement: [Amy Dubanowski, coworker, Glenn Sturgis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glenn Sturgis
Context triple: [Amy Dubanowski, coworker, Glenn Sturgis]
  • A. Glenn Sturgis chosen
    Glenn Sturgis is a devout, overly cheerful store manager and central comedic character on the television sitcom "Superstore."
  • B. Glenn Dennis
    Glenn Dennis was a New Mexico mortician and key Roswell incident witness who co-founded the International UFO Museum and Research Center in Roswell.
  • C. Glen Hardin
    Glen Hardin is an American pianist and arranger best known for his work with Elvis Presley’s TCB Band and influential contributions to rock and country music.
  • D. Merrill Stubing
    Merrill Stubing is the dignified, paternal captain of the cruise ship at the center of the classic television series "The Love Boat."
  • E. Glenn Patterson
    Glenn Patterson is a Northern Irish novelist and commentator known for his works exploring the social and political landscape of Belfast and contemporary Ireland.
  • 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_69d85a1551a08190ba2caea7cd51c639 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e7727a081908eff45bbc1633c8a completed April 16, 2026, 1:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0035450810819092796c556dfa8ed3 completed May 10, 2026, 7:35 a.m.
Created at: April 10, 2026, 3:19 a.m.