Triple

T20387646
Position Surface form Disambiguated ID Type / Status
Subject Winona Kirk E497998 entity
Predicate relative P37 FINISHED
Object George Kirk 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: George Kirk | Statement: [Winona Kirk, relative, George Kirk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Kirk
Context triple: [Winona Kirk, relative, George Kirk]
  • A. George Kirk chosen
    George Kirk is a Starfleet officer in the Star Trek franchise, best known as the father of James T. Kirk who dies heroically during Nero’s attack in the 2009 film.
  • B. Kirk Lazarus
    Kirk Lazarus is a method-obsessed, Oscar-winning Australian actor portrayed by Robert Downey Jr. in the satirical war-comedy film "Tropic Thunder."
  • C. James Kirkland
    James Kirkland was a member of the Potsdam Giants, the elite regiment of exceptionally tall soldiers in the army of Frederick William I of Prussia.
  • D. Frank Shepard
    Frank Shepard was an American legal publisher and innovator best known for developing the Shepard's Citations system used to track the subsequent history and treatment of legal cases.
  • E. Kirk Baxter
    Kirk Baxter is an Australian film editor best known for his Academy Award–winning collaborations with director David Fincher on films such as "The Social Network" and "The Girl with the Dragon Tattoo."
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790c935881908f901d058e6a83a9 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.