Triple

T17623666
Position Surface form Disambiguated ID Type / Status
Subject Hollywood Wives E429773 entity
Predicate screenwriter P2831 FINISHED
Object Jackie Collins 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: Jackie Collins | Statement: [Hollywood Wives, screenwriter, Jackie Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jackie Collins
Context triple: [Hollywood Wives, screenwriter, Jackie Collins]
  • A. Jackie Collins chosen
    Jackie Collins was a bestselling British-American novelist known for her glamorous, scandal-filled tales of Hollywood life, including the popular "Hollywood Wives" series.
  • B. Christina Holt
    Christina Holt is a family member of Dr. Michael Holt, a connection that places her within his immediate personal and familial circle.
  • C. Linda Howard
    Linda Howard is a fictional protagonist featured in the film "Lost in America."
  • D. Mary Ludlum
    Mary Ludlum was the wife of American thriller novelist Robert Ludlum, known for supporting him throughout his writing career.
  • E. Francine Rivers
    Francine Rivers is a bestselling American author known for her inspirational Christian fiction novels, particularly "Redeeming Love."
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dba664c81909dcaf44779db5565 completed April 19, 2026, 5:52 a.m.
Created at: April 10, 2026, 5:52 a.m.