Triple

T15748701
Position Surface form Disambiguated ID Type / Status
Subject Pronto card E381789 entity
Predicate replaces P101 FINISHED
Object Compass Card E723805 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: Compass Card | Statement: [Pronto card, replaces, Compass Card]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Compass Card
Context triple: [Pronto card, replaces, Compass Card]
  • A. Compass Card chosen
    Compass Card is a reloadable smart card used as the primary electronic fare payment system for public transit in Metro Vancouver, Canada.
  • B. Compass Card
    Compass Card is a reusable smart fare card used for paying transit fares across the San Diego Metropolitan Transit System and North County Transit District.
  • C. Metcard
    Metcard was Melbourne’s former magnetic stripe ticketing system used for public transport before the introduction of the Myki smartcard.
  • D. Breeze Card
    The Breeze Card is a reusable smart fare card used for paying transit fares across the Metropolitan Atlanta Rapid Transit Authority (MARTA) system in Atlanta, Georgia.
  • E. 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.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0502fd3608190b42e647b9c2b41a1 completed April 16, 2026, 2:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9094b4008190bb5c65fa2bd0f0b5 completed May 9, 2026, 7:52 p.m.
Created at: April 10, 2026, 4:46 a.m.