Triple

T1860680
Position Surface form Disambiguated ID Type / Status
Subject Tokyo Metro E34803 entity
Predicate acceptsCard P15672 FINISHED
Object Suica E131332 NE FINISHED

How this triple was built (3 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: Suica | Statement: [Tokyo Metro, acceptsCard, Suica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suica
Context triple: [Tokyo Metro, acceptsCard, Suica]
  • A. Suica chosen
    Suica is a rechargeable contactless smart card issued by JR East that is widely used for train fares and electronic payments across Japan.
  • B. PASMO
    PASMO is a rechargeable contactless smart card widely used for public transportation and electronic payments across the Tokyo metropolitan area.
  • C. ICOCA
    ICOCA is a rechargeable contactless smart card used for fare payment on public transportation systems in the Kansai region of Japan.
  • D. Myki
    Myki is Melbourne’s contactless smartcard public transport ticketing system used across trains, trams, and buses in Victoria, Australia.
  • E. ORCA card
    The ORCA card is a reusable, contactless smart card used to pay fares across multiple public transit systems in the Puget Sound region of Washington State.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: acceptsCard
Context triple: [Tokyo Metro, acceptsCard, Suica]
  • A. supportsTapToPay chosen
    Indicates that an entity enables or is compatible with tap-to-pay (contactless) payment functionality.
  • B. supportsLoyaltyCards
    Indicates that an entity provides functionality to accept, manage, or work with loyalty cards for rewards or benefits.
  • C. cardType
    Indicates the classification or category assigned to a card within a given system or context.
  • D. creditCheckRequired
    Indicates that a verification of an entity’s creditworthiness must be performed before proceeding with a related action or transaction.
  • E. supportsOpenLoopPayments
    Indicates that an entity enables or is compatible with open-loop payment methods, where transactions are processed over general-purpose payment networks rather than a closed, proprietary system.
  • F. None of above.

Provenance (4 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb231de14819091da3a20ed03c430 completed March 7, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1ce296c819093336cbaa257dfd2 completed March 8, 2026, 7:45 p.m.
PD Predicate disambiguation batch_69abafde4598819099d8229128348fd3 completed March 7, 2026, 4:55 a.m.
Created at: March 4, 2026, 7:34 p.m.