Triple

T18494949
Position Surface form Disambiguated ID Type / Status
Subject Jeremy Hardy E451920 entity
Predicate name P16 FINISHED
Object Jeremy Hardy 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: Jeremy Hardy | Statement: [Jeremy Hardy, name, Jeremy Hardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeremy Hardy
Context triple: [Jeremy Hardy, name, Jeremy Hardy]
  • A. Jeremy Hardy chosen
    Jeremy Hardy was a British comedian and radio personality known for his sharp political satire and long-running appearances on BBC Radio 4 panel shows.
  • B. Richard Fairbrass
    Richard Fairbrass is an English musician and television presenter best known as the lead singer of the pop band Right Said Fred.
  • C. Lewis Kingman
    Lewis Kingman was a 19th-century civil engineer and railroad surveyor whose work on the Atlantic and Pacific Railroad led to the Arizona city of Kingman being named in his honor.
  • D. Harvey Postlethwaite
    Harvey Postlethwaite was a prominent British Formula One engineer and designer best known for his influential work on innovative and competitive race cars for several top teams during the 1970s–1990s.
  • E. George Scales
    George Scales was an American Negro league baseball infielder and manager known for his strong hitting and leadership during the 1920s and 1930s.
  • 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_69d8d3855d50819097fc8561b0299dd9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e532bfeef4819096b2fa28abb662b9 completed April 19, 2026, 7:53 p.m.
Created at: April 10, 2026, 11:35 a.m.