Triple

T5085321
Position Surface form Disambiguated ID Type / Status
Subject Riga International Airport E114621 entity
Predicate hubFor P423 FINISHED
Object airBaltic E491072 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: airBaltic | Statement: [Riga International Airport, hubFor, airBaltic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: airBaltic
Context triple: [Riga International Airport, hubFor, airBaltic]
  • A. airBaltic chosen
    airBaltic is the flag carrier airline of Latvia, operating a network of flights across Europe and beyond from its main hub in Riga.
  • B. Crossair
    Crossair was a former Swiss regional airline that served as the main predecessor to Swiss International Air Lines after the collapse of Swissair.
  • C. Lynx Air
    Lynx Air is a Canadian ultra-low-cost airline that operates domestic and select international flights, primarily serving major hubs such as Toronto Pearson International Airport.
  • D. Air Europa
    Air Europa is a Spanish airline that operates domestic and international flights, serving as one of Spain’s major carriers and a member of the SkyTeam alliance.
  • E. Adria Airways
    Adria Airways was the former national airline of Slovenia, operating scheduled and charter flights across Europe before ceasing operations in 2019.
  • 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_69bd443e941881908eb4e8c685b6f656 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd751db4f4819088b998d7af0e6f41 completed March 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb13a8be08190a0f1fc3aec224dde completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:40 p.m.