Triple

T22889849
Position Surface form Disambiguated ID Type / Status
Subject Melbourne tram route 70 E567705 entity
Predicate fareSystem P395 FINISHED
Object myki 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: myki | Statement: [Melbourne tram route 70, fareSystem, myki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: myki
Context triple: [Melbourne tram route 70, fareSystem, myki]
  • A. Myki chosen
    Myki is Melbourne’s contactless smartcard public transport ticketing system used across trains, trams, and buses in Victoria, Australia.
  • B. Myki Pass
    Myki Pass is a prepaid, time-based public transport ticket used for unlimited travel within selected zones on Victoria’s Myki system.
  • C. Myki Zone 15
    Myki Zone 15 is a regional public transport fare zone in Victoria, Australia, covering areas including Echuca and surrounding localities on the state’s rail network.
  • D. Myki Zone 16
    Myki Zone 16 is an outer regional public transport fare zone in Victoria, Australia, covering areas including Swan Hill railway station.
  • E. Myki Zone 1
    Myki Zone 1 is the primary metropolitan public transport fare zone covering central and inner-suburban Melbourne, used for trains, trams, and buses on the Myki ticketing system.
  • 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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17fc479d48190a8218eceaebd6cc8 completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.