Triple

T18078501
Position Surface form Disambiguated ID Type / Status
Subject Mary Archer E432622 entity
Predicate spouse P13 FINISHED
Object Jeffrey Archer NE NERFINISHED

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: Jeffrey Archer | Statement: [Mary Archer, spouse, Jeffrey Archer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeffrey Archer
Context triple: [Mary Archer, spouse, Jeffrey Archer]
  • A. Jeffrey Archer chosen
    Jeffrey Archer is a British author and former politician best known for his bestselling novels and thrillers.
  • 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. Reginald Hill
    Reginald Hill was a British crime novelist best known for his long-running Dalziel and Pascoe detective series.
  • E. Winston Graham
    Winston Graham was a British novelist best known for writing the historical Poldark series set in 18th-century Cornwall.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4d9f6a85481909894c39c8be98d5d completed April 19, 2026, 1:34 p.m.
Created at: April 10, 2026, 10:27 a.m.