Triple

T4358468
Position Surface form Disambiguated ID Type / Status
Subject Bedales School E98607 entity
Predicate notableAlumni P51 FINISHED
Object Gyles Brandreth E409442 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: Gyles Brandreth | Statement: [Bedales School, notableAlumni, Gyles Brandreth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gyles Brandreth
Context triple: [Bedales School, notableAlumni, Gyles Brandreth]
  • A. Gyles Brandreth chosen
    Gyles Brandreth is a British writer, broadcaster, former Conservative MP, and television personality known for his wit, wordplay, and appearances on radio and panel shows.
  • B. Giles Paxman
    Giles Paxman is a British former diplomat who served as the United Kingdom's ambassador to Mexico and later to Spain.
  • C. Giles Nuttgens
    Giles Nuttgens is a British cinematographer known for his visually distinctive work on independent films and major features, often collaborating with directors like Deepa Mehta and David Mackenzie.
  • D. Clive Tolley
    Clive Tolley is a Canadian municipal politician who has served as the mayor of Moose Jaw, Saskatchewan.
  • E. Roger Howells
    Roger Howells is a relatively obscure individual whose name is notably recorded as a bearer of the surname Howells.
  • 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_69b3454c772081908e20173e379e8ebe completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b351c7fa1881908bdc844a7142eb65 completed March 12, 2026, 11:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5dbbcb6188190a8a4da6a080f0d61 completed March 14, 2026, 10:05 p.m.
Created at: March 12, 2026, 11:16 p.m.