Triple

T15735690
Position Surface form Disambiguated ID Type / Status
Subject Graham O'Brien E381463 entity
Predicate appearsInEpisode P795 FINISHED
Object "Spyfall" E71118 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: "Spyfall" | Statement: [Graham O'Brien, appearsInEpisode, "Spyfall"]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: "Spyfall"
Context triple: [Graham O'Brien, appearsInEpisode, "Spyfall"]
  • A. The Spy
    "The Spy" is an 1821 historical novel by James Fenimore Cooper set during the American Revolutionary War, often regarded as one of the earliest major works of American fiction.
  • B. The Spy
    The Spy is a film featuring Russian actress Svetlana Khodchenkova in a prominent role within a Cold War espionage narrative.
  • C. Spyfall chosen
    Spyfall is a two-part Doctor Who television story featuring the Thirteenth Doctor facing a global conspiracy involving mysterious alien beings and the return of the Master.
  • D. Single Spies
    Single Spies is a play by British writer Alan Bennett that dramatizes episodes from the lives of Cambridge spies Guy Burgess and Anthony Blunt with his characteristic blend of wit and political insight.
  • E. SPY
    SPY is the SPDR S&P 500 ETF, a widely traded fund that tracks the performance of the S&P 500 stock market index.
  • 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.