Triple

T15927457
Position Surface form Disambiguated ID Type / Status
Subject Zardoz E386238 entity
Predicate starring P1507 FINISHED
Object John Alderton E960467 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 Alderton | Statement: [Zardoz, starring, John Alderton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Alderton
Context triple: [Zardoz, starring, John Alderton]
  • A. John Alderton chosen
    John Alderton is an English actor best known for his roles in television series such as "Please Sir!", "Upstairs, Downstairs," and "Thomas & Sarah."
  • B. Michael Fagan
    Michael Fagan is a British man best known for breaking into Buckingham Palace and entering Queen Elizabeth II’s bedroom in 1982, one of the most notorious royal security breaches in modern history.
  • C. Andrew Shepherd
    Andrew Shepherd is the fictional widowed U.S. President portrayed by Michael Douglas in the romantic political film "The American President."
  • D. Neil Johnston
    Neil Johnston was a dominant 1950s NBA center and Hall of Famer known for leading the league in scoring with the Philadelphia Warriors.
  • E. Neil Johnston
    Neil Johnston is the husband of English actress Sue Johnston, known for her roles in television series such as "Brookside" and "The Royle Family."
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156872964819083a2fb9f86df61ba completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5b0833081909668c042234b5b75 completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:52 a.m.