Triple

T7891150
Position Surface form Disambiguated ID Type / Status
Subject Juancho E. Yrausquin Airport E183236 entity
Predicate IATAcode P418 FINISHED
Object SAB
SAB is the three-letter IATA airport code for Juancho E. Yrausquin Airport, the small Caribbean airport serving the island of Saba in the Netherlands.
 E696445 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: SAB | Statement: [Juancho E. Yrausquin Airport, IATAcode, SAB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAB
Context triple: [Juancho E. Yrausquin Airport, IATAcode, SAB]
  • A. SAB
    SAB is the School of American Ballet, a premier ballet academy in New York City that serves as the official training school for the New York City Ballet.
  • B. SABE
    SABE is the ICAO airport code for Aeroparque Jorge Newbery, a major domestic and regional airport serving Buenos Aires, Argentina.
  • C. SB
    SB is the abbreviated name for the School of Basic Sciences, an academic unit focused on foundational scientific disciplines.
  • D. SB
    SB is the vehicle registration code used on license plates for cars registered in the city of Bielsko-Biała in southern Poland.
  • E. SB
    SB was the communist-era secret police and intelligence service of the Polish People's Republic, known for surveillance, repression, and political control.
  • 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: SAB
Triple: [Juancho E. Yrausquin Airport, IATAcode, SAB]
Generated description
SAB is the three-letter IATA airport code for Juancho E. Yrausquin Airport, the small Caribbean airport serving the island of Saba in the Netherlands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAB
Target entity description: SAB is the three-letter IATA airport code for Juancho E. Yrausquin Airport, the small Caribbean airport serving the island of Saba in the Netherlands.
  • A. SAB
    SAB is the School of American Ballet, a premier ballet academy in New York City that serves as the official training school for the New York City Ballet.
  • B. SABE
    SABE is the ICAO airport code for Aeroparque Jorge Newbery, a major domestic and regional airport serving Buenos Aires, Argentina.
  • C. SB
    SB is the vehicle registration code used on license plates for cars registered in the city of Bielsko-Biała in southern Poland.
  • D. SB
    SB is the abbreviated name for the School of Basic Sciences, an academic unit focused on foundational scientific disciplines.
  • E. SB
    SB was the communist-era secret police and intelligence service of the Polish People's Republic, known for surveillance, repression, and political control.
  • 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_69ca828c474c8190a254d6499871eaff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39ee137081908e87e35016c3a176 completed March 31, 2026, 3:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5ba51ee48190b654a931da2c049f completed March 31, 2026, 5:29 a.m.
NEDg Description generation batch_69cb5f1e84fc8190b535016cb69405b4 completed March 31, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_69cb769944d08190ba8c2f5fe76e037b completed March 31, 2026, 7:24 a.m.
Created at: March 30, 2026, 5 p.m.