Triple

T12182568
Position Surface form Disambiguated ID Type / Status
Subject Poldark E290255 entity
Predicate screenwriter P2831 FINISHED
Object Debbie Horsfield E968365 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: Debbie Horsfield | Statement: [Poldark, screenwriter, Debbie Horsfield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Debbie Horsfield
Context triple: [Poldark, screenwriter, Debbie Horsfield]
  • A. Debbie Horsfield chosen
    Debbie Horsfield is a British television writer and producer best known for creating and adapting popular drama series, including the acclaimed BBC adaptation of "Poldark."
  • B. Debbie Forsyth
    Debbie Forsyth is a child of the late British television entertainer and game show host Bruce Forsyth.
  • C. Debbie Honeywood
    Debbie Honeywood is a British actress best known for her lead role in Ken Loach’s social-realist drama film "Sorry We Missed You."
  • D. Deborah Watling
    Deborah Watling was an English actress best known for playing the companion Victoria Waterfield in the classic Doctor Who television series.
  • E. Debbie Hall
    Debbie Hall is a musician best known as a member of the alternative rock band Concrete Blonde.
  • 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_69d6ab64de5881908d56eb7a75c6cc69 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d915fd8dac8190928059ad2b6bbbf3 completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a8a92688190867b3e7191c3f43e completed May 2, 2026, 2:30 p.m.
Created at: April 8, 2026, 9:50 p.m.