Triple

T19847243
Position Surface form Disambiguated ID Type / Status
Subject Manitoba College E476897 entity
Predicate successor P78 FINISHED
Object United College 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: United College | Statement: [Manitoba College, successor, United College]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: United College
Context triple: [Manitoba College, successor, United College]
  • A. United College
    United College is one of the historic constituent colleges of the University of St Andrews in Scotland, responsible for much of the university’s academic and administrative life.
  • B. United College
    United College is an affiliated college of the University of Waterloo that provides academic programs, residence, and community-focused learning experiences for students.
  • C. United College
    United College is one of the constituent colleges of The Chinese University of Hong Kong, known for its strong emphasis on whole-person education and a close-knit residential community.
  • D. United College chosen
    United College was a Canadian higher education institution that later evolved into the University of Winnipeg.
  • E. Jordan College
    Jordan College is a fictional Oxford college in Philip Pullman’s "His Dark Materials" series, serving as the childhood home and academic setting for the protagonist Lyra Belacqua.
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65809da2c8190bb579ef42513b74d completed April 20, 2026, 4:44 p.m.
Created at: April 10, 2026, 1:51 p.m.