Triple

T968673
Position Surface form Disambiguated ID Type / Status
Subject William Banting E20895 entity
Predicate name P16 FINISHED
Object William Banting E20895 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: William Banting | Statement: [William Banting, name, William Banting]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Banting
Context triple: [William Banting, name, William Banting]
  • A. William Banting chosen
    William Banting is the son of Canadian physician and Nobel laureate Frederick Banting, co-discoverer of insulin.
  • B. Frederick Banting
    Frederick Banting was a Canadian medical scientist and physician best known for co-discovering insulin, a breakthrough that revolutionized the treatment of diabetes and earned him the Nobel Prize in Physiology or Medicine.
  • C. Charles Best
    Charles Best was a Canadian physiologist best known for co-discovering insulin alongside Frederick Banting, a breakthrough that revolutionized the treatment of diabetes.
  • D. Elliott P. Joslin
    Elliott P. Joslin was a pioneering American physician and one of the first diabetes specialists, renowned for advancing diabetes research, treatment, and patient education.
  • E. B. B. Collip
    B. B. Collip was a Canadian biochemist best known as a key member of the team that developed insulin as a treatment for diabetes.
  • 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_69a493b33d2c81909c52c369d3ca8436 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b4481f508190adcf0a965a23862c completed March 1, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5992e4a88190b10b98efd24c3616 completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:40 p.m.