Triple

T17048747
Position Surface form Disambiguated ID Type / Status
Subject Terminal 4 E413638 entity
Predicate locatedIn P40 FINISHED
Object Václav Havel Airport Prague 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: Václav Havel Airport Prague | Statement: [Terminal 4, locatedIn, Václav Havel Airport Prague]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Václav Havel Airport Prague
Context triple: [Terminal 4, locatedIn, Václav Havel Airport Prague]
  • A. Václav Havel Airport Prague chosen
    Václav Havel Airport Prague is the main international airport serving Prague and the largest airport in the Czech Republic.
  • B. Karlovy Vary Airport
    Karlovy Vary Airport is a regional international airport in the Czech Republic serving the spa city of Karlovy Vary and its surrounding area.
  • C. Hradec Králové Airport
    Hradec Králové Airport is a regional civil and general aviation airport serving the city of Hradec Králové in the Czech Republic.
  • D. Leoš Janáček Airport Ostrava
    Leoš Janáček Airport Ostrava is an international airport in the Czech Republic serving the city of Ostrava and the surrounding Moravian-Silesian region.
  • E. Pardubice Airport
    Pardubice Airport is a regional international airport in the Czech Republic that serves both civilian and military air traffic.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3daa092f08190a9e37404a9de662c completed April 18, 2026, 7:25 p.m.
Created at: April 10, 2026, 5:34 a.m.