Triple

T19282968
Position Surface form Disambiguated ID Type / Status
Subject Sir Fred Hollows E482235 entity
Predicate name P16 FINISHED
Object Fred Hollows 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: Fred Hollows | Statement: [Sir Fred Hollows, name, Fred Hollows]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fred Hollows
Context triple: [Sir Fred Hollows, name, Fred Hollows]
  • A. Sir Fred Hollows chosen
    Sir Fred Hollows was a renowned New Zealand–Australian ophthalmologist and humanitarian best known for his work restoring eyesight to thousands of people in disadvantaged communities around the world.
  • B. Graeme Clark
    Graeme Clark is a Scottish musician best known as the bassist and a founding member of the pop band Wet Wet Wet.
  • C. Graeme Clark
    Graeme Clark is an Australian medical researcher and pioneer of the multi-channel cochlear implant, which has restored hearing to hundreds of thousands of deaf people worldwide.
  • D. Vaughan Johnson
    Vaughan Johnson was an American professional football linebacker best known for his Pro Bowl career with the New Orleans Saints as part of their famed "Dome Patrol" defense.
  • E. Richard Horton
    Richard Horton is a British medical doctor and editor best known for serving as the long-time editor-in-chief of the influential medical journal The Lancet.
  • 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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fbffda78819088bf8dbc61756831 completed April 20, 2026, 10:12 a.m.
Created at: April 10, 2026, 1:30 p.m.