Triple

T19109598
Position Surface form Disambiguated ID Type / Status
Subject Radcliffe Trust E467751 entity
Predicate namedAfter P63 FINISHED
Object John Radcliffe 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: John Radcliffe | Statement: [Radcliffe Trust, namedAfter, John Radcliffe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Radcliffe
Context triple: [Radcliffe Trust, namedAfter, John Radcliffe]
  • A. John Radcliffe chosen
    John Radcliffe was an influential 17th-century English physician and royal doctor whose wealth funded several major buildings at the University of Oxford.
  • B. John Aston
    John Aston is an actor known for his role in the film "The Navigators."
  • C. Jeremy Northam
    Jeremy Northam is an English actor known for his versatile film and television roles, including period dramas and character-driven ensemble pieces.
  • D. Clive Standen
    Clive Standen is a British actor best known for his roles in historical and action television series such as Vikings and Taken.
  • E. Rowland Leigh
    Rowland Leigh was a British screenwriter and lyricist active in the early to mid-20th century, known for his work on Hollywood films and stage musicals.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e392ef488190a230b1d2890b2a9d completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:04 p.m.