Triple

T2352016
Position Surface form Disambiguated ID Type / Status
Subject The Black Dahlia E47468 entity
Predicate authorOfSourceWork P2353 FINISHED
Object James Ellroy E140362 NE FINISHED

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: James Ellroy | Statement: [The Black Dahlia, authorOfSourceWork, James Ellroy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Ellroy
Context triple: [The Black Dahlia, authorOfSourceWork, James Ellroy]
  • A. James Ellroy chosen
    James Ellroy is an American crime fiction writer renowned for his dark, intricately plotted L.A. Quartet novels and his stylized, staccato prose.
  • B. Mickey Spillane
    Mickey Spillane was an American crime novelist best known for his hard-boiled Mike Hammer detective series.
  • C. Michael Connelly
    Michael Connelly is a bestselling American crime fiction author best known for his Harry Bosch and Lincoln Lawyer series.
  • D. John D. MacDonald
    John D. MacDonald was an American novelist best known for his hardboiled crime and suspense fiction, including the Travis McGee series.
  • E. Elmore Leonard
    Elmore Leonard was an American novelist and screenwriter renowned for his gritty crime fiction, sharp dialogue, and works such as "Rum Punch," "Get Shorty," and "Out of Sight."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88a1b678c8190bce986922ba60ce0 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc6f8ff548190b07505310e2bf0b9 completed March 7, 2026, 6:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9631c9a481909a3051ac06afdca7 completed March 9, 2026, 9:43 a.m.
Created at: March 4, 2026, 7:54 p.m.