Triple

T2635417
Position Surface form Disambiguated ID Type / Status
Subject Azul Brazilian Airlines E59733 entity
Predicate ICAOcode P419 FINISHED
Object AZU
AZU is the ICAO airline designator for Azul Brazilian Airlines, a major low-cost carrier based in Brazil.
 E283415 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: AZU | Statement: [Azul Brazilian Airlines, ICAOcode, AZU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AZU
Context triple: [Azul Brazilian Airlines, ICAOcode, AZU]
  • A. AZO
    AZO is the stock ticker symbol for AutoZone, a major American retailer and distributor of automotive replacement parts and accessories.
  • B. AZD
    AZD is a common shorthand used to refer to the Arizona Diamondbacks, a Major League Baseball team based in Phoenix, Arizona.
  • C. UZ
    UZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Uzbekistan.
  • D. Azzi
    Azzi is the surname of Jennifer Azzi, a former American professional basketball player and Olympic gold medalist.
  • E. ZUE
    ZUE is the railway station code for Zürich Hauptbahnhof, Switzerland’s largest and busiest train station and a major European rail hub.
  • 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: AZU
Triple: [Azul Brazilian Airlines, ICAOcode, AZU]
Generated description
AZU is the ICAO airline designator for Azul Brazilian Airlines, a major low-cost carrier based in Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AZU
Target entity description: AZU is the ICAO airline designator for Azul Brazilian Airlines, a major low-cost carrier based in Brazil.
  • A. AZO
    AZO is the stock ticker symbol for AutoZone, a major American retailer and distributor of automotive replacement parts and accessories.
  • B. AZD
    AZD is a common shorthand used to refer to the Arizona Diamondbacks, a Major League Baseball team based in Phoenix, Arizona.
  • C. UZ
    UZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Uzbekistan.
  • D. Azzi
    Azzi is the surname of Jennifer Azzi, a former American professional basketball player and Olympic gold medalist.
  • E. ZUE
    ZUE is the railway station code for Zürich Hauptbahnhof, Switzerland’s largest and busiest train station and a major European rail hub.
  • 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_69ab4ac8596c8190b34997e73d9e991c completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8e085b0819089db4103c0d8cd9b completed March 7, 2026, 7:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69af90ac94d48190b3138abac9934ec8 completed March 10, 2026, 3:31 a.m.
NEDg Description generation batch_69af91625bd481908d3666af3cd3733f completed March 10, 2026, 3:34 a.m.
NED2 Entity disambiguation (via description) batch_69af91f9e1208190aa149c9afc84911c completed March 10, 2026, 3:37 a.m.
Created at: March 6, 2026, 9:50 p.m.