Triple

T15067410
Position Surface form Disambiguated ID Type / Status
Subject Taiwan Railways network E379789 entity
Predicate acceptsCard P15672 FINISHED
Object iPASS E376163 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: iPASS | Statement: [Taiwan Railways network, acceptsCard, iPASS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: iPASS
Context triple: [Taiwan Railways network, acceptsCard, iPASS]
  • A. iPASS chosen
    iPASS is a Taiwanese contactless smart card widely used for public transportation fares and small-value electronic payments.
  • B. I-PASS
    I-PASS is an electronic toll collection system used on Illinois tollways that allows drivers to pay tolls automatically without stopping.
  • C. PASPA
    PASPA was a 1992 U.S. federal law that effectively banned state-authorized sports betting nationwide until it was struck down by the Supreme Court in 2018.
  • D. OnePass
    OnePass was Continental Airlines’ frequent flyer loyalty program that allowed passengers to earn and redeem miles for flights and travel rewards.
  • E. Telepass
    Telepass is an Italian electronic toll collection system that allows drivers to pay motorway and other transport-related fees automatically without stopping at toll booths.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedeebc7e48190a86b4f0afe8844bb completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69fea5cb04e88190a42bb0e516df61bc completed May 9, 2026, 3:11 a.m.
Created at: April 10, 2026, 3:02 a.m.