Triple

T18857935
Position Surface form Disambiguated ID Type / Status
Subject Université du Québec E461222 entity
Predicate abbreviation P43 FINISHED
Object UQ 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: UQ | Statement: [Université du Québec, abbreviation, UQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UQ
Context triple: [Université du Québec, abbreviation, UQ]
  • A. UQ chosen
    UQ is the abbreviation for the Université du Québec, a public university system comprising multiple institutions across the province of Quebec, Canada.
  • B. UQ mobile
    UQ mobile is a Japanese mobile virtual network operator offering affordable smartphone and data services, operated under KDDI.
  • C. D-Q University
    D-Q University was a short-lived, Native American and Chicano-focused tribal college in California known for its role in Indigenous and civil rights education.
  • D. CQU
    CQU is the station code for Circular Quay railway station on Sydney's suburban rail network.
  • E. CQU
    CQU is the commonly used abbreviation for Chongqing University, a major national research university located in Chongqing, China.
  • 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_69d8dcfb7b9c8190854e7b171b98ea2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c05de3e88190b0bfcbce906daa5e completed April 20, 2026, 5:57 a.m.
Created at: April 10, 2026, 11:57 a.m.