Triple

T21158675
Position Surface form Disambiguated ID Type / Status
Subject Collège Boréal E521377 entity
Predicate hasCampusIn P4623 FINISHED
Object Hearst, Ontario 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: Hearst, Ontario | Statement: [Collège Boréal, hasCampusIn, Hearst, Ontario]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hearst, Ontario
Context triple: [Collège Boréal, hasCampusIn, Hearst, Ontario]
  • A. Hearst, Ontario chosen
    Hearst, Ontario is a small bilingual (French-English) town in northern Ontario known for its forestry-based economy and strong Franco-Ontarian culture.
  • B. Hawkesbury, Ontario
    Hawkesbury, Ontario is a small bilingual town on the Ottawa River known for its manufacturing history and position between Ottawa and Montreal.
  • C. Galt, Ontario
    Galt, Ontario was a historic town in southern Ontario that later became one of the constituent communities of the city of Cambridge.
  • D. Latimer, Ontario
    Latimer, Ontario is a small rural community located within the township of South Frontenac in eastern Ontario, Canada.
  • E. Hickson, Ontario
    Hickson, Ontario is a small rural community located within Oxford County in southwestern Ontario, Canada.
  • 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7252e9ef481908f4904c535f3da8b completed April 21, 2026, 7:20 a.m.
Created at: April 16, 2026, 2:59 p.m.