Triple

T20876932
Position Surface form Disambiguated ID Type / Status
Subject Little Women (1994 film) E514040 entity
Predicate storyBy P1955 FINISHED
Object Allan Knee 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: Allan Knee | Statement: [Little Women (1994 film), storyBy, Allan Knee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Allan Knee
Context triple: [Little Women (1994 film), storyBy, Allan Knee]
  • A. Allan Knee chosen
    Allan Knee is an American playwright and screenwriter best known for creating the stage play that inspired the film "Finding Neverland."
  • B. Allan Carpenter
    Allan Carpenter is a fictional character best known as the protagonist of the time-travel novel "The Door into Summer" by Robert A. Heinlein.
  • C. Allan Little
    Allan Little is a British journalist and former BBC correspondent known for his in-depth reporting on international conflicts and political affairs.
  • D. Doug Allan
    Doug Allan is a renowned British wildlife cameraman and cinematographer, particularly celebrated for his work on marine and polar documentaries.
  • E. Allan Cooke
    Allan Cooke was a founder associated with the establishment and early development of the town of Cookstown.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c6767ec0819080721e2e75bd0d66 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:45 p.m.