Triple

T16842331
Position Surface form Disambiguated ID Type / Status
Subject Gyles Brandreth E409442 entity
Predicate coHostWith P5275 FINISHED
Object Susie Dent E851693 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: Susie Dent | Statement: [Gyles Brandreth, coHostWith, Susie Dent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susie Dent
Context triple: [Gyles Brandreth, coHostWith, Susie Dent]
  • A. Susie Dent chosen
    Susie Dent is a British lexicographer and etymologist best known for her long-running role as the resident word expert on the television game show "Countdown."
  • B. Susie McDonald
    Susie McDonald was one of the key plaintiffs in the landmark civil rights case Browder v. Gayle, which led to the desegregation of public buses in Montgomery, Alabama.
  • C. Suzie Toller
    Suzie Toller is a central, scheming character in the neo-noir thriller film "Wild Things," known for her role in the movie’s intricate web of deception and plot twists.
  • D. Susie Moss
    Susie Moss is best known as the wife of legendary British racing driver Sir Stirling Moss and a prominent figure in the motor racing community.
  • E. Jenny Dennison
    Jenny Dennison is a character in the Hocus Pocus franchise, known as the younger sister of Dani Dennison.
  • 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_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b35167a48190b45a459023e3ab1b completed April 18, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb199168819080a9ddc7534f19a7 completed May 10, 2026, 5:06 p.m.
Created at: April 10, 2026, 5:24 a.m.