Triple

T23318808
Position Surface form Disambiguated ID Type / Status
Subject China Kong E590788 entity
Predicate notableWork P4 FINISHED
Object White of the Eye 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: White of the Eye | Statement: [China Kong, notableWork, White of the Eye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: White of the Eye
Context triple: [China Kong, notableWork, White of the Eye]
  • A. White of the Eye chosen
    White of the Eye is a 1987 British psychological horror-thriller film directed by Donald Cammell, noted for its stylized visuals and disturbing portrait of a serial killer in a small Arizona town.
  • B. Sight for Sore Eyes
    "Sight for Sore Eyes" is a hard rock song by Aerosmith from their 1977 album *Draw the Line*.
  • C. The Man with the Dancing Eyes
    The Man with the Dancing Eyes is a whimsical illustrated novella by Sophie Dahl that tells a romantic, fairy-tale-like story set in bohemian London.
  • D. The Whites of Their Eyes
    "The Whites of Their Eyes" is a historical work by Jill Lepore that examines how contemporary political movements reinterpret and mythologize the American Revolution.
  • E. The Blind Eye
    The Blind Eye is a poetry collection by Scottish poet Don Paterson, noted for its intricate formal craft and philosophical depth.
  • 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_69e25d1d32188190948eb76909d1dcc3 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1978372948190bad066893c4e0768 completed April 29, 2026, 5:30 a.m.
Created at: April 17, 2026, 5:07 p.m.