Triple

T6685739
Position Surface form Disambiguated ID Type / Status
Subject Lord Coe E152094 entity
Predicate birthName P65 FINISHED
Object Sebastian Newbold Coe E47738 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: Sebastian Newbold Coe | Statement: [Lord Coe, birthName, Sebastian Newbold Coe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sebastian Newbold Coe
Context triple: [Lord Coe, birthName, Sebastian Newbold Coe]
  • A. Sebastian Coe chosen
    Sebastian Coe is a British middle-distance running legend and double Olympic 1500m champion who later became a prominent sports administrator and president of World Athletics.
  • B. Colin Jackson
    Colin Jackson is a retired Welsh hurdler and sprinter best known for being a world champion and former world record holder in the 110 metres hurdles.
  • C. Philip Hampson Knight
    Philip Hampson Knight is an American billionaire businessman best known as the co-founder and longtime CEO of Nike, Inc.
  • D. Peter Coe
    Peter Coe was a British-born American actor and occasional director known for his character roles in mid-20th-century film and television.
  • E. Peter Snell
    Peter Snell is a British film producer best known for his work on notable 1970s films, including the cult horror classic "The Wicker Man."
  • 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_69c687f9977c819097e7f5ada4fe522e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b14cd6748190aad4badd5f253478 completed March 27, 2026, 4:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7b0c0148190a232ed10950ec92b completed March 27, 2026, 9:33 p.m.
Created at: March 27, 2026, 2:04 p.m.