Triple

T15735700
Position Surface form Disambiguated ID Type / Status
Subject Graham O'Brien E381463 entity
Predicate travelsWith P881 FINISHED
Object Yasmin Khan E354207 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: Yasmin Khan | Statement: [Graham O'Brien, travelsWith, Yasmin Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yasmin Khan
Context triple: [Graham O'Brien, travelsWith, Yasmin Khan]
  • A. Yasmin Khan chosen
    Yasmin Khan is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
  • B. Tasmina Ahmed-Sheikh
    Tasmina Ahmed-Sheikh is a Scottish politician, solicitor, and broadcaster known for her roles in pro-independence politics, including senior positions in both the SNP and the Alba Party.
  • C. Shabana Mahmood
    Shabana Mahmood is a British Labour Party politician and barrister who has served as a Member of Parliament and held senior frontbench roles.
  • D. Reham Khan
    Reham Khan is a British-Pakistani journalist, television presenter, and author who gained widespread public attention through her brief marriage to Pakistani politician and former cricketer Imran Khan.
  • E. Yasmin Siraj
    Yasmin Siraj is an American former competitive figure skater known for her strong junior-level performances and appearances at U.S. national championships.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd586a88190aa1b1b88368d386f completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff8300a4248190ba52573b57f31b36 completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.