Triple

T20610024
Position Surface form Disambiguated ID Type / Status
Subject Silk E506423 entity
Predicate executiveProducer P7225 FINISHED
Object Hilary Salmon 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: Hilary Salmon | Statement: [Silk, executiveProducer, Hilary Salmon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hilary Salmon
Context triple: [Silk, executiveProducer, Hilary Salmon]
  • A. Hilary Salmon chosen
    Hilary Salmon is a British television producer known for her executive production work on acclaimed BBC dramas and adaptations.
  • B. Hilary Wainwright
    Hilary Wainwright is a British socialist feminist writer and academic known for her work on participatory democracy, left politics, and radical social movements.
  • C. Larissa Howard
    Larissa Howard is known as the daughter of British military historian and politician Michael Howard.
  • D. Hilary Jeffkins
    Hilary Jeffkins is a television producer best known for her work on the British nature documentary series "Wild Isles."
  • E. Sara Hutchinson
    Sara Hutchinson was an English woman closely associated with the Romantic poet Samuel Taylor Coleridge, often remembered as his muse and confidante.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aad6f53481908fb242947dda7028 completed April 20, 2026, 10:38 p.m.
Created at: April 16, 2026, 11:41 a.m.