Triple

T16760378
Position Surface form Disambiguated ID Type / Status
Subject Kurt Waldheim E407325 entity
Predicate givenName P17 FINISHED
Object Kurt E102649 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: Kurt | Statement: [Kurt Waldheim, givenName, Kurt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurt
Context triple: [Kurt Waldheim, givenName, Kurt]
  • A. Kurt chosen
    Kurt is a given name most famously associated with the logician and mathematician Kurt Gödel.
  • B. Kurt
    Kurt is a close associate of Scott Lang in the Marvel universe, known as one of his quirky ex-con partners in crime and heists.
  • C. Kurt Frederick
    Kurt Frederick was a conductor best known for leading the premiere performance of Arnold Schoenberg’s cantata "A Survivor from Warsaw."
  • D. Kurt Christian
    Kurt Christian is a British actor best known for his roles in 1970s fantasy and adventure films, particularly in Ray Harryhausen–associated productions.
  • E. Kurt Midness
    Kurt Midness is a member of the RTX band, known for its experimental and noise-influenced rock music.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abec638c81909d71ff452a4123c9 completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52b17b88190af24c04d16980c9f completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:21 a.m.