Triple

T22124913
Position Surface form Disambiguated ID Type / Status
Subject Gong Li E546767 entity
Predicate notableWork P4 FINISHED
Object The Banquet 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: The Banquet | Statement: [Gong Li, notableWork, The Banquet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Banquet
Context triple: [Gong Li, notableWork, The Banquet]
  • A. The Banquet
    The Banquet is the English title of Dante Alighieri’s unfinished philosophical work "Convivio," which blends prose and poetry to explore ethics, politics, and knowledge.
  • B. The Banquet chosen
    The Banquet is a 2006 Chinese wuxia drama film loosely based on Shakespeare's Hamlet, known for its lavish visuals and starring Zhang Ziyi.
  • C. The Heavenly Banquet
    The Heavenly Banquet is a song from Samuel Barber’s "Hermit Songs," Op. 29, setting a medieval Irish monastic text to music in an intimate art-song style.
  • D. Taming the Feast
    Taming the Feast is a cookbook by chef Ben Ford that focuses on large-scale, rustic outdoor feasts and whole-animal cooking.
  • E. The Dinner
    The Dinner is a psychological drama film adapted from Herman Koch’s novel, centering on two couples whose tense restaurant conversation gradually reveals a disturbing family secret.
  • 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_69e11e39bf348190b541bfa16a7b71e0 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12980e2488190b58b541c8bee8480 completed April 28, 2026, 9:41 p.m.
Created at: April 16, 2026, 8:31 p.m.