Triple

T13864663
Position Surface form Disambiguated ID Type / Status
Subject Iğdır E333289 entity
Predicate hasAirport P105 FINISHED
Object Iğdır Airport
Iğdır Airport is a public airport in eastern Turkey serving the city and province of Iğdır with domestic flights.
E1066184 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: Iğdır Airport | Statement: [Iğdır, hasAirport, Iğdır Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iğdır Airport
Context triple: [Iğdır, hasAirport, Iğdır Airport]
  • A. Muş Airport
    Muş Airport is a regional public airport in eastern Turkey that serves the city of Muş and its surrounding area with domestic flights.
  • B. Oğuzeli Airport
    Oğuzeli Airport is the main public airport serving the city and province of Gaziantep in southeastern Turkey.
  • C. Ağrı Ahmed-i Hani Airport
    Ağrı Ahmed-i Hani Airport is a regional public airport in eastern Turkey serving the city and province of Ağrı with domestic flights.
  • D. Sivas Nuri Demirağ Airport
    Sivas Nuri Demirağ Airport is a public airport serving the city and province of Sivas in central Turkey, providing domestic and limited international air connections.
  • E. Erzurum Airport
    Erzurum Airport is a public airport serving the city of Erzurum in eastern Turkey, handling both domestic and limited international flights.
  • 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: Iğdır Airport
Triple: [Iğdır, hasAirport, Iğdır Airport]
Generated description
Iğdır Airport is a public airport in eastern Turkey serving the city and province of Iğdır with domestic flights.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Iğdır Airport
Target entity description: Iğdır Airport is a public airport in eastern Turkey serving the city and province of Iğdır with domestic flights.
  • A. Muş Airport
    Muş Airport is a regional public airport in eastern Turkey that serves the city of Muş and its surrounding area with domestic flights.
  • B. Oğuzeli Airport
    Oğuzeli Airport is the main public airport serving the city and province of Gaziantep in southeastern Turkey.
  • C. Ağrı Ahmed-i Hani Airport
    Ağrı Ahmed-i Hani Airport is a regional public airport in eastern Turkey serving the city and province of Ağrı with domestic flights.
  • D. Sivas Nuri Demirağ Airport
    Sivas Nuri Demirağ Airport is a public airport serving the city and province of Sivas in central Turkey, providing domestic and limited international air connections.
  • E. Erzurum Airport
    Erzurum Airport is a public airport serving the city of Erzurum in eastern Turkey, handling both domestic and limited international flights.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c30d9c81908217d41a3b4aaf85 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c10113288190b799126d934df92a completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c1e7efd88190ac07472647da69e7 completed May 3, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3396f7c8190987079bf24ac8695 completed May 3, 2026, 9:50 p.m.
Created at: April 9, 2026, 10:14 p.m.