Triple

T7273881
Position Surface form Disambiguated ID Type / Status
Subject Terminal 2 (Dublin Airport) E162975 entity
Predicate IATAAirportCode P418 FINISHED
Object DUB E153718 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: DUB | Statement: [Terminal 2 (Dublin Airport), IATAAirportCode, DUB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DUB
Context triple: [Terminal 2 (Dublin Airport), IATAAirportCode, DUB]
  • A. DUB chosen
    DUB is the three-letter IATA airport code for Dublin Airport, the main international gateway to Dublin and the Republic of Ireland.
  • B. U-Dub
    U-Dub is a common nickname for the University of Washington, a major public research university in Seattle known for its strong academic and athletic programs.
  • C. DUS
    DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
  • D. Didube
    Didube is a metro station in Tbilisi, Georgia, serving as a key transit hub that connects the city’s metro system with major bus and marshrutka routes to other regions.
  • E. Debub
    Debub is a southern administrative region of Eritrea known for its highland landscapes, agriculture, and historical sites.
  • 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_69c6885c5964819085b209701769877f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb0de9f48190807dd148758bad62 completed March 27, 2026, 8:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db2936dc8190aed38888bb5e47b8 completed March 28, 2026, 1:44 p.m.
Created at: March 27, 2026, 2:58 p.m.