Triple

T1419322
Position Surface form Disambiguated ID Type / Status
Subject Kenya Airways E31986 entity
Predicate hasCodeShareAgreementWith P10967 FINISHED
Object Precision Air
Precision Air is a Tanzanian airline that operates regional and domestic flights within East Africa.
 E162779 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: Precision Air | Statement: [Kenya Airways, hasCodeShareAgreementWith, Precision Air]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Precision Air
Context triple: [Kenya Airways, hasCodeShareAgreementWith, Precision Air]
  • A. J-Air
    J-Air is a Japanese regional airline operating domestic feeder and short-haul routes on behalf of Japan Airlines.
  • B. Ramport Aero
    Ramport Aero is the company responsible for managing and operating Zhukovsky International Airport near Moscow, Russia.
  • C. Luchtcomponent
    Luchtcomponent is the Dutch name for the air component of the Belgian Armed Forces, responsible for Belgium’s military aviation operations.
  • D. Experiments on Air
    Experiments on Air is an influential scientific work by Henry Cavendish detailing his pioneering investigations into the properties and composition of gases, including the study of hydrogen.
  • E. Aira Force
    Aira Force is a picturesque waterfall in England’s Lake District, renowned for its dramatic cascades, woodland trails, and stone arch bridge.
  • 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: Precision Air
Triple: [Kenya Airways, hasCodeShareAgreementWith, Precision Air]
Generated description
Precision Air is a Tanzanian airline that operates regional and domestic flights within East Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Precision Air
Target entity description: Precision Air is a Tanzanian airline that operates regional and domestic flights within East Africa.
  • A. J-Air
    J-Air is a Japanese regional airline operating domestic feeder and short-haul routes on behalf of Japan Airlines.
  • B. Ramport Aero
    Ramport Aero is the company responsible for managing and operating Zhukovsky International Airport near Moscow, Russia.
  • C. Luchtcomponent
    Luchtcomponent is the Dutch name for the air component of the Belgian Armed Forces, responsible for Belgium’s military aviation operations.
  • D. Experiments on Air
    Experiments on Air is an influential scientific work by Henry Cavendish detailing his pioneering investigations into the properties and composition of gases, including the study of hydrogen.
  • E. Aira Force
    Aira Force is a picturesque waterfall in England’s Lake District, renowned for its dramatic cascades, woodland trails, and stone arch bridge.
  • 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_69a49919a994819086528951bc224775 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c4915bfc8190a631330b7c495b49 completed March 1, 2026, 10:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69ace5857d6c8190902eecd7bb12cbaf completed March 8, 2026, 2:57 a.m.
NEDg Description generation batch_69ace78168f481908133d74a52a7f6c9 completed March 8, 2026, 3:05 a.m.
NED2 Entity disambiguation (via description) batch_69aceb4ac6bc8190a3d0b44f922d5302 completed March 8, 2026, 3:21 a.m.
Created at: March 1, 2026, 7:59 p.m.