Triple

T5471676
Position Surface form Disambiguated ID Type / Status
Subject Gyumri E122847 entity
Predicate hasAirport P105 FINISHED
Object Shirak Airport
Shirak Airport is an international airport serving the city of Gyumri in northwestern Armenia, functioning as one of the country’s main civilian air gateways.
E523407 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: Shirak Airport | Statement: [Gyumri, hasAirport, Shirak Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shirak Airport
Context triple: [Gyumri, hasAirport, Shirak Airport]
  • A. Sary-Arka Airport
    Sary-Arka Airport is the main international airport serving the city of Karaganda in central Kazakhstan.
  • B. Almaza Airport
    Almaza Airport is a historic airfield in Cairo that served as the city's main airport before the opening of Cairo International Airport.
  • C. Nadym Airport
    Nadym Airport is a regional airport in Nadym, Russia, primarily serving as a key base for operations in the Yamalo-Nenets Autonomous Okrug.
  • D. Garowe Airport
    Garowe Airport is the main civil aviation facility serving the city of Garowe, the capital of the Puntland region in northeastern Somalia.
  • E. Kohat Airport
    Kohat Airport is a domestic airport serving the city of Kohat in Khyber Pakhtunkhwa, Pakistan.
  • 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: Shirak Airport
Triple: [Gyumri, hasAirport, Shirak Airport]
Generated description
Shirak Airport is an international airport serving the city of Gyumri in northwestern Armenia, functioning as one of the country’s main civilian air gateways.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shirak Airport
Target entity description: Shirak Airport is an international airport serving the city of Gyumri in northwestern Armenia, functioning as one of the country’s main civilian air gateways.
  • A. Sary-Arka Airport
    Sary-Arka Airport is the main international airport serving the city of Karaganda in central Kazakhstan.
  • B. Almaza Airport
    Almaza Airport is a historic airfield in Cairo that served as the city's main airport before the opening of Cairo International Airport.
  • C. Nadym Airport
    Nadym Airport is a regional airport in Nadym, Russia, primarily serving as a key base for operations in the Yamalo-Nenets Autonomous Okrug.
  • D. Garowe Airport
    Garowe Airport is the main civil aviation facility serving the city of Garowe, the capital of the Puntland region in northeastern Somalia.
  • E. Kohat Airport
    Kohat Airport is a domestic airport serving the city of Kohat in Khyber Pakhtunkhwa, Pakistan.
  • 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_69bd46459ff48190823377457bcf7128 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd921d02188190b5c1eee7205ea88e completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf4895b77c819089629d2296a230bc completed March 22, 2026, 1:40 a.m.
NEDg Description generation batch_69bf4c43b8bc81908b28e1b8287400c7 completed March 22, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_69bf4cadc9508190a901a6fe6702f1b7 completed March 22, 2026, 1:58 a.m.
Created at: March 20, 2026, 2:09 p.m.