Triple

T7160645
Position Surface form Disambiguated ID Type / Status
Subject AY E166932 entity
Predicate airlineFoundedAs P30178 FINISHED
Object Aero O/Y
Aero O/Y was the original Finnish airline that later evolved into the national carrier Finnair.
 E645849 NE FINISHED

How this triple was built (4 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: Aero O/Y | Statement: [AY, airlineFoundedAs, Aero O/Y]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Aero O/Y
Context triple: [AY, airlineFoundedAs, Aero O/Y]
  • A. Ulstein
    Ulstein is a coastal municipality in western Norway known for its maritime industry and shipbuilding.
  • B. B-67 Nuuk
    B-67 Nuuk is a prominent football club based in Nuuk, Greenland, known for its success in the Greenlandic football championship.
  • C. Fisker
    Fisker is a Danish surname most notably associated with architect Kay Fisker and, more broadly, with several prominent Danish figures in design, architecture, and the arts.
  • D. Granma yacht
    The Granma yacht is the vessel that carried Fidel Castro and his revolutionaries from Mexico to Cuba in 1956, marking the beginning of the Cuban Revolution.
  • E. Gjøa
    Gjøa is the historic Norwegian polar exploration ship used by Roald Amundsen to complete the first successful navigation of the Northwest Passage.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Aero O/Y
Triple: [AY, airlineFoundedAs, Aero O/Y]
Generated description
Aero O/Y was the original Finnish airline that later evolved into the national carrier Finnair.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Aero O/Y
Target entity description: Aero O/Y was the original Finnish airline that later evolved into the national carrier Finnair.
  • A. Ulstein
    Ulstein is a coastal municipality in western Norway known for its maritime industry and shipbuilding.
  • B. B-67 Nuuk
    B-67 Nuuk is a prominent football club based in Nuuk, Greenland, known for its success in the Greenlandic football championship.
  • C. Fisker
    Fisker is a Danish surname most notably associated with architect Kay Fisker and, more broadly, with several prominent Danish figures in design, architecture, and the arts.
  • D. Granma yacht
    The Granma yacht is the vessel that carried Fidel Castro and his revolutionaries from Mexico to Cuba in 1956, marking the beginning of the Cuban Revolution.
  • E. Gjøa
    Gjøa is the historic Norwegian polar exploration ship used by Roald Amundsen to complete the first successful navigation of the Northwest Passage.
  • F. None of above. chosen

Provenance (5 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_69c7adc08b688190a00024727542c8b9 completed March 28, 2026, 10:30 a.m.
NEDg Description generation batch_69c7ae661f4481908ee489023af9603b completed March 28, 2026, 10:33 a.m.
NED2 Entity disambiguation (via description) batch_69c7aef767848190b7edf7a99e2e019d completed March 28, 2026, 10:35 a.m.
Created at: March 27, 2026, 2:47 p.m.