Triple

T22124934
Position Surface form Disambiguated ID Type / Status
Subject Gong Li E546767 entity
Predicate notableWork P4 FINISHED
Object The Story of a Geisha 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 Story of a Geisha | Statement: [Gong Li, notableWork, The Story of a Geisha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Story of a Geisha
Context triple: [Gong Li, notableWork, The Story of a Geisha]
  • A. Memoirs of a Geisha
    Memoirs of a Geisha is a 2005 film adaptation of Arthur Golden’s novel, depicting the life of a young girl sold to a geisha house in pre- and post-World War II Japan.
  • B. The Geisha Boy
    The Geisha Boy is a 1958 American comedy film starring Jerry Lewis as a bumbling magician entertaining U.S. troops in Japan.
  • C. The Barbarian and the Geisha
    The Barbarian and the Geisha is a 1958 historical drama film directed by John Huston and starring John Wayne as an American diplomat in 19th-century Japan.
  • D. The Story of a Courtesan chosen
    The Story of a Courtesan is a film featuring acclaimed Chinese actress Gong Li in a central role.
  • E. The Life of Oharu
    The Life of Oharu is a 1952 Japanese period drama film directed by Kenji Mizoguchi that chronicles the tragic downfall of a samurai’s daughter in feudal Japan.
  • 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.