Triple

T8093734
Position Surface form Disambiguated ID Type / Status
Subject Deansgate-Castlefield E188931 entity
Predicate hasLine P35 FINISHED
Object Airport Line E5769 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: Airport Line | Statement: [Deansgate-Castlefield, hasLine, Airport Line]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airport Line
Context triple: [Deansgate-Castlefield, hasLine, Airport Line]
  • A. Airport Line chosen
    The Airport Line is a Manchester Metrolink light rail route that connects central Manchester with Manchester Airport, serving key suburbs and transport interchanges along the way.
  • B. Airport Line
    Airport Line is a SEPTA Regional Rail service in the Philadelphia area that connects Center City with Philadelphia International Airport.
  • C. Airport Line
    Airport Line is a Wuhan Metro route that connects the city’s urban rail network with its main airport, providing rapid transit access for air travelers.
  • D. Airport Line
    Airport Line is a railway line in Japan that connects urban areas to Kansai International Airport, operated by the private Nankai Electric Railway company.
  • E. Airport line
    The Airport line is a railway service in Brisbane, Australia that connects the city to Brisbane Airport, providing dedicated public transport access for air travelers.
  • 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_69ca82b7b3e88190b9041ab0ef28b3cb completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4222b68c81909c8bc326763240d0 completed March 31, 2026, 3:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc93ff6a108190ac60218ec2716c60 completed April 1, 2026, 3:41 a.m.
Created at: March 30, 2026, 5:30 p.m.