Triple

T8660287
Position Surface form Disambiguated ID Type / Status
Subject Swissair E205529 entity
Predicate foundedBy P104 FINISHED
Object Balair
Balair was a Swiss charter airline that operated primarily leisure and holiday flights, and later became part of the Swissair Group.
 E748921 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: Balair | Statement: [Swissair, foundedBy, Balair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Balair
Context triple: [Swissair, foundedBy, Balair]
  • A. Balantak
    Balantak is an Austronesian language of central Sulawesi, Indonesia, closely related to and often grouped with the Saluan language.
  • B. Barbalha
    Barbalha is a municipality in northeastern Brazil known for its traditional cultural festivals and location in the state of Ceará.
  • C. Ballu
    Ballu is a French surname most notably associated with architect Albert Ballu.
  • D. Bala
    Bala is a small historic market town in Gwynedd, Wales, best known for its proximity to Llyn Tegid (Bala Lake), the largest natural lake in Wales.
  • E. Bala
    Bala is a small community in Ontario, Canada, known for its scenic lakeside setting in the Muskoka region and its popular Bala Cranberry Festival.
  • 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: Balair
Triple: [Swissair, foundedBy, Balair]
Generated description
Balair was a Swiss charter airline that operated primarily leisure and holiday flights, and later became part of the Swissair Group.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Balair
Target entity description: Balair was a Swiss charter airline that operated primarily leisure and holiday flights, and later became part of the Swissair Group.
  • A. Balantak
    Balantak is an Austronesian language of central Sulawesi, Indonesia, closely related to and often grouped with the Saluan language.
  • B. Barbalha
    Barbalha is a municipality in northeastern Brazil known for its traditional cultural festivals and location in the state of Ceará.
  • C. Ballu
    Ballu is a French surname most notably associated with architect Albert Ballu.
  • D. Bala
    Bala is a small historic market town in Gwynedd, Wales, best known for its proximity to Llyn Tegid (Bala Lake), the largest natural lake in Wales.
  • E. Bala
    Bala is a small community in Ontario, Canada, known for its scenic lakeside setting in the Muskoka region and its popular Bala Cranberry Festival.
  • 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_69ca8350897c819086cde7596fbe5fe7 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc48701c748190a5f7bd9e2da0e5e9 completed March 31, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ceccfda1dc8190a3b93b1c7e813f33 completed April 2, 2026, 8:09 p.m.
NEDg Description generation batch_69cece8d530081908f5a52d5d76bd414 completed April 2, 2026, 8:16 p.m.
NED2 Entity disambiguation (via description) batch_69cecf7c66308190b9fb87bc0ab510a8 completed April 2, 2026, 8:20 p.m.
Created at: March 30, 2026, 6:30 p.m.