Triple

T18590269
Position Surface form Disambiguated ID Type / Status
Subject Peter Jones E454346 entity
Predicate name P16 FINISHED
Object Peter Jones — 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: Peter Jones | Statement: [Peter Jones, name, Peter Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Peter Jones
Context triple: [Peter Jones, name, Peter Jones]
  • A. Peter Jones
    Peter Jones is a well-known John Lewis department store located on Sloane Square in London, recognized for its wide range of quality goods and prominent position in the Chelsea shopping district.
  • B. Peter Jones chosen
    Peter Jones is a British entrepreneur, investor, and television personality best known as a long-standing "dragon" on the BBC series Dragons' Den.
  • C. Peter Jones
    Peter Jones was a British actor and comedian best known for his distinctive voice work, including as the narrator in the original radio series of "The Hitchhiker’s Guide to the Galaxy."
  • D. Peter Jones
    Peter Jones is a television producer known for his work on the food-related series "Finding Food."
  • E. Mark Jones
    Mark Jones is an actor known for his role in the film "From Hand to Mouth."
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e545b4a2a0819098047ee81278bd9d completed April 19, 2026, 9:14 p.m.
Created at: April 10, 2026, 11:44 a.m.