Triple

T6635723
Position Surface form Disambiguated ID Type / Status
Subject The Deadly Affair E150444 entity
Predicate novelPublicationAuthor P2353 FINISHED
Object John le Carré E48060 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: John le Carré | Statement: [The Deadly Affair, novelPublicationAuthor, John le Carré]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John le Carré
Context triple: [The Deadly Affair, novelPublicationAuthor, John le Carré]
  • A. John le Carré chosen
    John le Carré was a renowned British novelist best known for his sophisticated espionage thrillers that explored the moral ambiguities of Cold War intelligence work.
  • B. Len Deighton
    Len Deighton is a British author and historian best known for his spy novels, including "The IPCRESS File," and his influential works on military history.
  • C. Frederick Forsyth
    Frederick Forsyth is a British thriller writer renowned for his meticulously researched, politically charged novels such as "The Day of the Jackal."
  • D. Ian Fleming
    Ian Fleming was a British author and journalist best known as the creator of the James Bond spy novels.
  • E. Philip Kerr
    Philip Kerr was a British author best known for his Bernie Gunther series of historical crime novels set in Nazi and post-war Germany.
  • 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_69c687f0ceb08190bf40807bfc605fa5 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6afcd9a608190a949eb55766d5701 completed March 27, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6eeed01608190bbc6461ac8c3cadb completed March 27, 2026, 8:56 p.m.
Created at: March 27, 2026, 1:59 p.m.