Triple

T7531129
Position Surface form Disambiguated ID Type / Status
Subject Sochi International Airport E178024 entity
Predicate IATAcode P418 FINISHED
Object AER
AER is the three-letter IATA airport code for Sochi International Airport, serving the Black Sea resort city of Sochi in Russia.
 E669530 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: AER | Statement: [Sochi International Airport, IATAcode, AER]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AER
Context triple: [Sochi International Airport, IATAcode, AER]
  • A. AER
    AER is a leading peer-reviewed academic journal in economics published by the American Economic Association.
  • B. Aero
    Aero is a high-performance, sport-oriented trim level used by Saab for its 9-3 and other models, typically featuring more powerful engines and upgraded equipment.
  • C. AAR
    AAR is the ICAO airline designator used to identify Asiana Airlines in international aviation operations and communications.
  • D. AAR
    AAR is the American Association of Railroads' wheel arrangement classification system commonly used to describe locomotive axle configurations in North America.
  • E. AAR
    AAR is the commonly used abbreviation for All-American Road, a designation for particularly scenic and culturally significant highways in the United States.
  • 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: AER
Triple: [Sochi International Airport, IATAcode, AER]
Generated description
AER is the three-letter IATA airport code for Sochi International Airport, serving the Black Sea resort city of Sochi in Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AER
Target entity description: AER is the three-letter IATA airport code for Sochi International Airport, serving the Black Sea resort city of Sochi in Russia.
  • A. AER
    AER is a leading peer-reviewed academic journal in economics published by the American Economic Association.
  • B. Aero
    Aero is a high-performance, sport-oriented trim level used by Saab for its 9-3 and other models, typically featuring more powerful engines and upgraded equipment.
  • C. AAR
    AAR is the ICAO airline designator used to identify Asiana Airlines in international aviation operations and communications.
  • D. AAR
    AAR is the American Association of Railroads' wheel arrangement classification system commonly used to describe locomotive axle configurations in North America.
  • E. AAR
    AAR is the commonly used abbreviation for All-American Road, a designation for particularly scenic and culturally significant highways in the United States.
  • 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_69c69f2acdbc8190b5a8320168c1d0ba completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f8217b1c8190b3db453cee0fc4fd completed March 27, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8463e08ac8190abd4d19b58067233 completed March 28, 2026, 9:21 p.m.
NEDg Description generation batch_69c846b326088190b93a32c70bcc97ca completed March 28, 2026, 9:22 p.m.
NED2 Entity disambiguation (via description) batch_69c8479490688190bc56b5a21d779b18 completed March 28, 2026, 9:26 p.m.
Created at: March 27, 2026, 3:47 p.m.