Triple

T16842877
Position Surface form Disambiguated ID Type / Status
Subject Sue Perkins E409456 entity
Predicate coHostedWith P5275 FINISHED
Object Mel Giedroyc E666644 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: Mel Giedroyc | Statement: [Sue Perkins, coHostedWith, Mel Giedroyc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mel Giedroyc
Context triple: [Sue Perkins, coHostedWith, Mel Giedroyc]
  • A. Mel Giedroyc chosen
    Mel Giedroyc is a British comedian, actress, and television presenter best known for co-hosting "The Great British Bake Off."
  • B. Noel Edmonds
    Noel Edmonds is a British television and radio presenter best known for hosting shows such as "Top of the Pops," "Noel's House Party," and "Deal or No Deal."
  • C. Dermot O'Leary
    Dermot O'Leary is a British-Irish television and radio presenter best known for hosting the UK version of "The X Factor" and his shows on BBC Radio 2.
  • D. Michael McIntyre
    Michael McIntyre is a British stand-up comedian and television presenter known for his high-energy observational comedy and popular arena tours.
  • E. Michael McIntyre
    Michael McIntyre is a music producer best known for his work on the Whitesnake album "Good to Be Bad."
  • 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_69e3b35284588190a1d6238438f3e70d 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.