Triple

T10830513
Position Surface form Disambiguated ID Type / Status
Subject Luton railway station E255605 entity
Predicate serves P98 FINISHED
Object Luton Airport E15779 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: Luton Airport | Statement: [Luton railway station, serves, Luton Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luton Airport
Context triple: [Luton railway station, serves, Luton Airport]
  • A. Luton Airport chosen
    Luton Airport is a major international airport north of London that serves as a key hub for low-cost airlines and short-haul European flights.
  • B. Stansted Airport
    Stansted Airport is a major international airport serving the London area, particularly known as a hub for low-cost and European short-haul flights.
  • C. Southend Airport
    Southend Airport is a regional international airport in Essex, England, serving the London area with passenger and cargo flights.
  • D. Bristol Airport
    Bristol Airport is a major regional airport in South West England serving domestic and international flights, notably as a key base for low-cost carriers like easyJet.
  • E. Coventry Airport
    Coventry Airport is a regional airport in the West Midlands of England that has historically handled charter, cargo, and general aviation flights.
  • 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_69d6aa8081448190a9324184f2bd1c26 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d744222288819093258b452569acab completed April 9, 2026, 6:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69de85a068b08190948c3ca32cdda147 completed April 14, 2026, 6:21 p.m.
Created at: April 8, 2026, 9:19 p.m.