Triple

T7231030
Position Surface form Disambiguated ID Type / Status
Subject Ijpe DeKoe E154901 entity
Predicate spouse P13 FINISHED
Object Thomas Kostura E186467 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: Thomas Kostura | Statement: [Ijpe DeKoe, spouse, Thomas Kostura]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Kostura
Context triple: [Ijpe DeKoe, spouse, Thomas Kostura]
  • A. Thomas Kostura chosen
    Thomas Kostura is an individual known for being a plaintiff in the landmark same-sex marriage recognition case Tanco v. Haslam in Tennessee.
  • B. Peter Medak
    Peter Medak is a Hungarian-born British film and television director known for works such as the crime biopic "The Krays" and the horror classic "The Changeling."
  • C. Michael Kuzak
    Michael Kuzak is a central attorney character on the television legal drama "L.A. Law," known for his idealism and high-profile courtroom battles.
  • D. Jim Konstanty
    Jim Konstanty was an American Major League Baseball relief pitcher best known for his standout 1950 season with the Philadelphia Phillies, during which he won the National League MVP award.
  • E. James Kondelik
    James Kondelik is a film editor and filmmaker known for his work on low-budget genre movies such as the fantasy action film "Avengers Grimm."
  • 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_69c68811dd1c8190ac460bb39e64e1f0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea0f09648190b285993556f704d5 completed March 27, 2026, 8:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7cc22a39481909a2f38014260f302 completed March 28, 2026, 12:40 p.m.
Created at: March 27, 2026, 2:54 p.m.