Triple

T17853898
Position Surface form Disambiguated ID Type / Status
Subject Louise Glaum E445879 entity
Predicate notableWork P4 FINISHED
Object The Leopard Woman 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 Leopard Woman | Statement: [Louise Glaum, notableWork, The Leopard Woman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Leopard Woman
Context triple: [Louise Glaum, notableWork, The Leopard Woman]
  • A. The Leopard Woman
    The Leopard Woman is a 1920 silent adventure film in which actress Jacqueline Logan delivered one of her most recognized performances.
  • B. The Leopard Man
    The Leopard Man is a 1943 atmospheric horror film noted for its psychological tension and innovative use of off-screen terror.
  • C. The Wolf Woman chosen
    The Wolf Woman is a 1916 American silent drama film starring Louise Glaum as a seductive and manipulative femme fatale.
  • D. The Jungle Goddess
    The Jungle Goddess is a 1922 silent adventure film featuring jungle exploits and early cinematic action, associated with actor Gordon Griffith.
  • E. The Eye of the Leopard
    The Eye of the Leopard is a novel by Swedish author Henning Mankell that explores themes of identity, colonialism, and cultural conflict through a Swedish man's experiences in Zambia.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e49001d8b881908c8d4efc3d7ff04f completed April 19, 2026, 8:19 a.m.
Created at: April 10, 2026, 10:17 a.m.