Triple

T17163924
Position Surface form Disambiguated ID Type / Status
Subject Belen Regional Airport E416555 entity
Predicate IATA code P2569 FINISHED
Object BRG
BRG is the three-letter IATA airport code assigned to Belen Regional Airport in Belen, New Mexico, United States.
 E1254058 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: BRG | Statement: [Belen Regional Airport, IATA code, BRG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BRG
Context triple: [Belen Regional Airport, IATA code, BRG]
  • A. BRG
    BRG is the stock ticker symbol for Borregaard, a Norwegian company specializing in advanced and sustainable biochemicals derived from wood.
  • B. BRG
    BRG is the station code for Braga railway station, a major rail hub in the city of Braga in northern Portugal.
  • C. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • D. BRL
    BRL is an abbreviation for the Brisbane Rugby League, a historic rugby league competition based in Brisbane, Australia.
  • E. BRL
    BRL was a U.S. Army research facility known for pioneering work in ballistics and early computing, including development of some of the first digital computers.
  • 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: BRG
Triple: [Belen Regional Airport, IATA code, BRG]
Generated description
BRG is the three-letter IATA airport code assigned to Belen Regional Airport in Belen, New Mexico, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BRG
Target entity description: BRG is the three-letter IATA airport code assigned to Belen Regional Airport in Belen, New Mexico, United States.
  • A. BRG
    BRG is the stock ticker symbol for Borregaard, a Norwegian company specializing in advanced and sustainable biochemicals derived from wood.
  • B. BRG
    BRG is the station code for Braga railway station, a major rail hub in the city of Braga in northern Portugal.
  • C. BRL
    BRL is the official currency code for the Brazilian real, the legal tender of Brazil.
  • D. BRL
    BRL is an abbreviation for the Brisbane Rugby League, a historic rugby league competition based in Brisbane, Australia.
  • E. BRL
    BRL was a U.S. Army research facility known for pioneering work in ballistics and early computing, including development of some of the first digital computers.
  • 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_69d886d279c081909f8ff1f743ddeb69 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f913c84481908bb5da8bcc6a2e62 completed April 18, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01483b827081909619ea691c4c0e1e completed May 11, 2026, 3:08 a.m.
NEDg Description generation batch_6a014a2f8fec8190b1303967a76ceb63 completed May 11, 2026, 3:17 a.m.
NED2 Entity disambiguation (via description) batch_6a014ab0be388190a6ce49cff469fe81 completed May 11, 2026, 3:19 a.m.
Created at: April 10, 2026, 5:37 a.m.