Triple

T7160649
Position Surface form Disambiguated ID Type / Status
Subject AY E166932 entity
Predicate airlineCallsign P13478 FINISHED
Object FINNAIR E27121 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: FINNAIR | Statement: [AY, airlineCallsign, FINNAIR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FINNAIR
Context triple: [AY, airlineCallsign, FINNAIR]
  • A. Finnair chosen
    Finnair is the flag carrier and largest airline of Finland, operating an extensive network of domestic and international flights with a strong focus on routes between Europe and Asia.
  • B. Aer Lingus
    Aer Lingus is the flag carrier airline of Ireland, operating international flights primarily between Ireland, Europe, and North America.
  • C. Flynas
    Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
  • D. Icelandair
    Icelandair is the flag carrier airline of Iceland, operating international flights that connect North America and Europe via its hub near Reykjavík.
  • E. Crossair
    Crossair was a former Swiss regional airline that served as the main predecessor to Swiss International Air Lines after the collapse of Swissair.
  • 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_69c68887a5cc8190bec0ea96227164f7 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e82ce770819081dccf7ffd50c2ab completed March 27, 2026, 8:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d37a6cd48190802094259213a57f completed March 28, 2026, 1:11 p.m.
Created at: March 27, 2026, 2:47 p.m.