Triple

T694660
Position Surface form Disambiguated ID Type / Status
Subject Société de transport de Montréal E13868 entity
Predicate usesTicketingSystem P1740 FINISHED
Object OPUS smart card system E85452 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: OPUS smart card system | Statement: [Société de transport de Montréal, usesTicketingSystem, OPUS smart card system]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OPUS smart card system
Context triple: [Société de transport de Montréal, usesTicketingSystem, OPUS smart card system]
  • A. OPUS card chosen
    The OPUS card is a reusable, contactless smart card used for public transit fare payment across the greater Montreal area and other regions in Quebec.
  • B. Presto card
    The Presto card is a reloadable smart card used for paying public transit fares across the Greater Toronto and Hamilton Area and other regions in Ontario, Canada.
  • C. Clipper card
    The Clipper card is a reloadable contactless smart card used to pay fares across multiple public transit systems in the San Francisco Bay Area.
  • D. TAP card
    The TAP card is a reusable contactless smart card used to pay fares across public transit systems in the Los Angeles County region.
  • E. Java Card
    Java Card is a technology that enables Java-based applications to run securely on smart cards and other resource-constrained, tamper-resistant devices.
  • 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_69a493406c408190957eeec9048a8fb6 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a0c3f39c8190a3014df428817492 completed March 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a637514c9081909938d0801f071fea completed March 3, 2026, 1:20 a.m.
Created at: March 1, 2026, 7:36 p.m.