Triple

T19732611
Position Surface form Disambiguated ID Type / Status
Subject Braathens Regional Airlines E473891 entity
Predicate brandName P1500 FINISHED
Object BRA
BRA is a Swedish regional airline operating domestic and short-haul European flights, known for serving smaller airports and business travelers.
E1393285 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: BRA | Statement: [Braathens Regional Airlines, brandName, BRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BRA
Context triple: [Braathens Regional Airlines, brandName, BRA]
  • A. BRA
    BRA is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Brazil in international standards and data systems.
  • B. BRA
    BRA is the commonly used acronym for the Boston Redevelopment Authority, the urban planning and economic development agency for the city of Boston.
  • C. BR
    BR is the upper house of Austria’s parliament, representing the federal states in the legislative process.
  • D. BR
    BR is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Brazil in international standards and systems.
  • E. BR
    BR is the commonly used abbreviation for Banco de la República, Colombia’s central bank responsible for monetary policy and currency issuance.
  • 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: BRA
Triple: [Braathens Regional Airlines, brandName, BRA]
Generated description
BRA is a Swedish regional airline operating domestic and short-haul European flights, known for serving smaller airports and business travelers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BRA
Target entity description: BRA is a Swedish regional airline operating domestic and short-haul European flights, known for serving smaller airports and business travelers.
  • A. BRA
    BRA is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Brazil in international standards and data systems.
  • B. BRA
    BRA is the commonly used acronym for the Boston Redevelopment Authority, the urban planning and economic development agency for the city of Boston.
  • C. BR
    BR is the IATA airline designator for EVA Air, a major Taiwanese international carrier based in Taoyuan.
  • D. BR
    BR is a postcode area in southeast London and parts of northwest Kent, covering towns such as Bromley and Beckenham.
  • E. BR
    BR is the official station code used to identify Burlington GO Station in Ontario, Canada.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e651596b98819090bcaf05c7b74555 completed April 20, 2026, 4:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07b4f4e1e081908fca0b6513bb3bbb completed May 16, 2026, 12:06 a.m.
NEDg Description generation batch_6a07b73cc5a48190af0ab9da30c859b4 completed May 16, 2026, 12:15 a.m.
NED2 Entity disambiguation (via description) batch_6a07b81193d081908dfb19272b4df41b completed May 16, 2026, 12:19 a.m.
Created at: April 10, 2026, 1:47 p.m.