Triple

T22176933
Position Surface form Disambiguated ID Type / Status
Subject University of Toronto insulin research team E548073 entity
Predicate collaborationWith P398 FINISHED
Object Connaught Laboratories NE NERFINISHED

How this triple was built (3 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: Connaught Laboratories | Statement: [University of Toronto insulin research team, collaborationWith, Connaught Laboratories]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Connaught Laboratories
Context triple: [University of Toronto insulin research team, collaborationWith, Connaught Laboratories]
  • A. Hudson Laboratories
    Hudson Laboratories was a research organization known for its work in underwater acoustics and oceanographic studies, particularly in support of U.S. Navy and defense-related projects.
  • B. Tartan Laboratories
    Tartan Laboratories was a computer science and software company known for its work on programming language tools and compilers, particularly in collaboration with prominent language designers like Guy L. Steele Jr.
  • C. Marion Laboratories
    Marion Laboratories was a prominent American pharmaceutical company best known for its rapid growth and eventual merger into Marion Merrell Dow, founded by entrepreneur and Kansas City Royals owner Ewing Kauffman.
  • D. Jenkins Laboratories
    Jenkins Laboratories was a pioneering research and development company associated with early motion picture and television innovations led by inventor Charles Francis Jenkins.
  • E. Bullard Laboratories
    Bullard Laboratories is a geophysics research facility at the University of Cambridge known for its work in seismology, geomagnetism, and the physics of the Earth's interior.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Connaught Laboratories
Target entity description: Connaught Laboratories was a Canadian public health and biopharmaceutical institution renowned for producing vaccines and insulin, playing a key role in making insulin widely available after its discovery.
  • A. Hudson Laboratories
    Hudson Laboratories was a research organization known for its work in underwater acoustics and oceanographic studies, particularly in support of U.S. Navy and defense-related projects.
  • B. Tartan Laboratories
    Tartan Laboratories was a computer science and software company known for its work on programming language tools and compilers, particularly in collaboration with prominent language designers like Guy L. Steele Jr.
  • C. Marion Laboratories
    Marion Laboratories was a prominent American pharmaceutical company best known for its rapid growth and eventual merger into Marion Merrell Dow, founded by entrepreneur and Kansas City Royals owner Ewing Kauffman.
  • D. Jenkins Laboratories
    Jenkins Laboratories was a pioneering research and development company associated with early motion picture and television innovations led by inventor Charles Francis Jenkins.
  • E. Bullard Laboratories
    Bullard Laboratories is a geophysics research facility at the University of Cambridge known for its work in seismology, geomagnetism, and the physics of the Earth's interior.
  • F. None of above. chosen

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_69e11e3d53f88190a2b690e3f25bb062 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a6d03488190b29872ff3f436237 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.