Triple

T3321842
Position Surface form Disambiguated ID Type / Status
Subject Foyle's War E69811 entity
Predicate hasCharacter P2308 FINISHED
Object Christopher Foyle E349162 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: Christopher Foyle | Statement: [Foyle's War, hasCharacter, Christopher Foyle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christopher Foyle
Context triple: [Foyle's War, hasCharacter, Christopher Foyle]
  • A. Christopher Foyle chosen
    Christopher Foyle is the principled, quietly determined British detective at the heart of the World War II-era crime drama series "Foyle's War."
  • B. Peter Robinson
    Peter Robinson is a Northern Irish politician who served as leader of the Democratic Unionist Party and First Minister of Northern Ireland.
  • C. Robert Grace
    Robert Grace was an early American civic leader and philanthropist known for his role in colonial Philadelphia’s public institutions and community organizations.
  • D. 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.
  • E. Harry Hart
    Harry Hart is a suave, highly skilled British secret agent and mentor figure in the Kingsman film series.
  • 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_69ad85a1829881908942c14075644d0d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb13d13a88190828d9a03fd0865ce completed March 8, 2026, 5:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bb5d0b88190b1895fd352924862 completed March 12, 2026, 11:26 p.m.
Created at: March 8, 2026, 3:11 p.m.