Triple

T20059692
Position Surface form Disambiguated ID Type / Status
Subject Metlink E499434 entity
Predicate hasMobileApp P1395 FINISHED
Object Metlink app NE NERFINISHED

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: Metlink app | Statement: [Metlink, hasMobileApp, Metlink app]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Metlink app
Context triple: [Metlink, hasMobileApp, Metlink app]
  • A. Metlink chosen
    Metlink is the public transport brand and coordinating agency for bus, rail, and ferry services in New Zealand’s Wellington region.
  • B. Metrolink eTicket app
    The Metrolink eTicket app is a mobile application that allows passengers to purchase, store, and display digital train tickets for travel on the Metrolink network.
  • C. MuniMobile app
    MuniMobile app is San Francisco’s official mobile ticketing application that lets riders purchase and use Muni transit fares directly from their smartphones.
  • D. CityLink
    CityLink is a network of color-coded, high-frequency bus routes that form the core of Baltimore’s modernized public transit system.
  • E. Moovit
    Moovit is a popular mobility-as-a-service app that provides real-time public transit information and navigation for cities worldwide.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66374f4a48190beb575a6c84ebdb4 completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:38 p.m.