Triple

T20775339
Position Surface form Disambiguated ID Type / Status
Subject Radcliffe Infirmary E511340 entity
Predicate architect P184 FINISHED
Object Stiff Leadbetter 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: Stiff Leadbetter | Statement: [Radcliffe Infirmary, architect, Stiff Leadbetter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stiff Leadbetter
Context triple: [Radcliffe Infirmary, architect, Stiff Leadbetter]
  • A. Stiff Leadbetter chosen
    Stiff Leadbetter was an 18th-century English architect and builder known for designing country houses and estates in a restrained Palladian style.
  • B. Red Hayes
    Red Hayes was an American country music songwriter and fiddler best known for co-writing the classic song "A Satisfied Mind."
  • C. Sidney Hickox
    Sidney Hickox was an American cinematographer known for his work on classic Hollywood films, particularly in the film noir and crime genres.
  • D. Dwan
    Dwan is the female lead character in the 1976 remake of King Kong, portrayed as the shipwrecked aspiring actress who forms a unique bond with the giant ape.
  • E. Glenn Talbot
    Glenn Talbot is a high-ranking U.S. military officer in Marvel Comics, best known as a persistent adversary of the Hulk and romantic rival to Betty Ross.
  • 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_69e0b4cac7a48190a715cb3d545df2b4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26b06ac81909aef3b0a0ad79a33 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.