Triple

T13669181
Position Surface form Disambiguated ID Type / Status
Subject Maradana railway station E327703 entity
Predicate railwayLine P848 FINISHED
Object Mannar Line E1012537 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: Mannar Line | Statement: [Maradana railway station, railwayLine, Mannar Line]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mannar Line
Context triple: [Maradana railway station, railwayLine, Mannar Line]
  • A. Mannar Line chosen
    Mannar Line is a railway line in Sri Lanka that connects the mainland rail network to the Mannar region in the country’s northwest.
  • B. Suigun Line
    The Suigun Line is a regional railway line in eastern Japan that connects Mito in Ibaraki Prefecture with inland areas, providing local passenger rail services through rural communities.
  • C. Ljabru Line
    The Ljabru Line is a tram line in Oslo, Norway, forming part of the city’s light rail network and serving the southeastern district of Ljabru.
  • D. Taita Line
    The Taita Line is a regional railway line in Japan connecting Gifu and Tajimi, serving as a local commuter and intercity link in central Honshu.
  • E. Tua Line
    Tua Line is a scenic narrow-gauge railway in northeastern Portugal, known for running along the Tua River through rugged, picturesque landscapes.
  • 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_69d8076f1fa8819094664a59b55010df completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc65832688190aea688fee0a7cbdb completed April 12, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78b0f56048190bcbc6581a8cdc0f5 completed May 3, 2026, 5:51 p.m.
Created at: April 9, 2026, 9:53 p.m.