Triple

T10354732
Position Surface form Disambiguated ID Type / Status
Subject Karla E243971 entity
Predicate creator P184 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: [Karla, creator, John le Carré]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John le Carré
Context triple: [Karla, creator, 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e952c878819084e5d7a593a3f9e9 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d750a30af88190b2ebf0daf758ed44 completed April 9, 2026, 7:09 a.m.
Created at: April 6, 2026, 11:58 a.m.