Triple

T17873322
Position Surface form Disambiguated ID Type / Status
Subject Jiří Kylián E446887 entity
Predicate influencedBy P9 FINISHED
Object John Cranko 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: John Cranko | Statement: [Jiří Kylián, influencedBy, John Cranko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Cranko
Context triple: [Jiří Kylián, influencedBy, John Cranko]
  • A. John Cranko chosen
    John Cranko was a renowned South African-born British choreographer and director, best known for his influential narrative ballets and leadership of the Stuttgart Ballet.
  • B. Alwin Nikolais
    Alwin Nikolais was an influential American choreographer and multimedia dance pioneer known for his abstract, theatrical works that integrated movement, lighting, costumes, and sound into unified stage compositions.
  • C. Jean-Claude Chermann
    Jean-Claude Chermann is a French virologist recognized for his key role in the discovery and characterization of the HIV virus.
  • D. Joseph Béjart
    Joseph Béjart was a 17th-century French actor and member of the Béjart theatrical family closely associated with Molière’s troupe.
  • E. Anton Karas
    Anton Karas was an Austrian zither player and composer best known for his iconic zither score for the film "The Third Man."
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa4959881908774dafb7be99191 completed April 19, 2026, 9:04 a.m.
Created at: April 10, 2026, 10:18 a.m.