Triple

T18150583
Position Surface form Disambiguated ID Type / Status
Subject Revelation of the Daleks E434489 entity
Predicate starsActor P5563 FINISHED
Object Nicola Bryant 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: Nicola Bryant | Statement: [Revelation of the Daleks, starsActor, Nicola Bryant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicola Bryant
Context triple: [Revelation of the Daleks, starsActor, Nicola Bryant]
  • A. Nicola Bryant chosen
    Nicola Bryant is an English actress best known for playing the Doctor Who companion Peri Brown during the 1980s.
  • B. Nicola Reynolds
    Nicola Reynolds is a Welsh actress best known for her role in the cult British film "Human Traffic" and for her work in UK television and theatre.
  • C. Nicola Blackwell
    Nicola Blackwell is an actress known for her role in the acclaimed British dance drama film "Billy Elliot."
  • D. Nicola Duffett
    Nicola Duffett is a British actress known for her work in television, film, and theatre, including roles in popular UK dramas and soap operas.
  • E. Nicola Marsh
    Nicola Marsh is a cinematographer best known for her work on the Oscar-winning documentary "20 Feet from Stardom."
  • 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_69d8b90aac308190801e2c57d8c5bfe5 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4de3812e8819097f025476d5c6a1d completed April 19, 2026, 1:52 p.m.
Created at: April 10, 2026, 10:29 a.m.