Triple

T7548766
Position Surface form Disambiguated ID Type / Status
Subject Metrolinx E178473 entity
Predicate operates P24 FINISHED
Object Union Pearson Express E587521 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: Union Pearson Express | Statement: [Metrolinx, operates, Union Pearson Express]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Union Pearson Express
Context triple: [Metrolinx, operates, Union Pearson Express]
  • A. Union–Pearson Express chosen
    Union–Pearson Express is a dedicated airport rail link in Toronto that provides fast, frequent train service between Union Station in downtown Toronto and Toronto Pearson International Airport.
  • B. Airport Express Line
    The Airport Express Line is a high-speed Delhi Metro corridor that connects central Delhi with Indira Gandhi International Airport, providing fast transit for air travelers and commuters.
  • C. Airport Express
    Airport Express is a high-speed rail service in Hong Kong that links the city center with Hong Kong International Airport.
  • D. AirTrain Newark
    AirTrain Newark is an automated monorail system that connects Newark Liberty International Airport’s terminals with parking areas and regional rail services.
  • E. Grand Central Airport
    Grand Central Airport is a small general aviation airport in Midrand, South Africa, primarily serving private, charter, and flight training operations.
  • 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_69c69f2cbe08819088f9eb0c03ef529b completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f89b9afc8190b3e61a8e2cea7ad7 completed March 27, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69c856bb83b88190947c0efed84b891a completed March 28, 2026, 10:31 p.m.
Created at: March 27, 2026, 3:49 p.m.