Triple

T18234417
Position Surface form Disambiguated ID Type / Status
Subject Guinness Peat Aviation E436632 entity
Predicate keyPerson P256 FINISHED
Object Aer Lingus 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: Aer Lingus | Statement: [Guinness Peat Aviation, keyPerson, Aer Lingus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aer Lingus
Context triple: [Guinness Peat Aviation, keyPerson, Aer Lingus]
  • A. Aer Lingus chosen
    Aer Lingus is the flag carrier airline of Ireland, operating international flights primarily between Ireland, Europe, and North America.
  • B. Ryanair
    Ryanair is a major Irish low-cost airline known for its extensive network of short-haul flights across Europe.
  • C. Aer Lingus AerClub
    Aer Lingus AerClub is the frequent-flyer loyalty program of Aer Lingus, allowing members to earn and redeem points on flights and partner services.
  • D. Flynas
    Flynas is a Saudi low-cost airline based in Riyadh that operates domestic and regional flights across the Middle East and beyond.
  • E. Icelandair
    Icelandair is the flag carrier airline of Iceland, operating international flights that connect North America and Europe via its hub near Reykjavík.
  • 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_69d8b9103a8081908bbb0836fef10efd completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f4b5ce608190b6fba518256607da completed April 19, 2026, 3:28 p.m.
Created at: April 10, 2026, 10:33 a.m.