Triple

T8998830
Position Surface form Disambiguated ID Type / Status
Subject LMB E214989 entity
Predicate hasNotableResearcher P14810 FINISHED
Object Tim Hunt E313838 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: Tim Hunt | Statement: [LMB, hasNotableResearcher, Tim Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tim Hunt
Context triple: [LMB, hasNotableResearcher, Tim Hunt]
  • A. Sir Tim Hunt chosen
    Sir Tim Hunt is a British biochemist and Nobel Prize laureate recognized for his discovery of key regulators of the cell cycle.
  • B. Richard Clements
    Richard Clements is a composer and musician known for creating the musical score for the film "Tap."
  • C. Fran Walsh
    Fran Walsh is a New Zealand screenwriter and film producer best known for her long-time creative partnership with Peter Jackson on films such as The Lord of the Rings trilogy, for which she won multiple Academy Awards.
  • D. Thomas Gerdine
    Thomas Gerdine was an early mountaineer known for making the first recorded ascent of Glacier Peak in Washington State.
  • E. John Dykstra Eusden
    John Dykstra Eusden was an American Reformed theologian and scholar known for his influential English translation and editing of William Ames’s classic work "The Marrow of Theology."
  • 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_69ca83a12d648190b1e4fe11e8a31890 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc68e23734819083a98f4ff0942479 completed April 1, 2026, 12:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0d987dc81908f1d74f390f18a9c completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:05 p.m.