Triple

T654130
Position Surface form Disambiguated ID Type / Status
Subject Université de Montréal E11608 entity
Predicate affiliation P10 FINISHED
Object CIS E36395 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: CIS | Statement: [Université de Montréal, affiliation, CIS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CIS
Context triple: [Université de Montréal, affiliation, CIS]
  • A. CIS chosen
    CIS (Canadian Interuniversity Sport) was the former national governing body for university athletics in Canada, overseeing intercollegiate sports competition before being rebranded as U Sports.
  • B. CIS
    The CIS (Commonwealth of Independent States) is a regional intergovernmental organization formed by several former Soviet republics to facilitate cooperation in political, economic, and security matters.
  • C. CSC
    CSC is the commonly used abbreviation for the Supreme Court of Canada, the country's highest judicial authority.
  • D. CIT
    CIT is the commonly used acronym for the Center for Information Technology, an organization focused on advancing computing and information systems.
  • E. NIS
    NIS (Network Information Service) is a client-server directory service protocol developed by Sun Microsystems to centrally manage and distribute system configuration data such as user and host information across Unix networks.
  • 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_69a4932862a0819098be659c814e4981 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49f4bb5b881908a18b5ec1c94e0cf completed March 1, 2026, 8:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69a591486b708190b0191e958c6c8851 completed March 2, 2026, 1:31 p.m.
Created at: March 1, 2026, 7:36 p.m.