Triple

T4179118
Position Surface form Disambiguated ID Type / Status
Subject Antalya Airport E86549 entity
Predicate IATAcode P418 FINISHED
Object AYT E84719 NE FINISHED

How this triple was built (2 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: AYT | Statement: [Antalya Airport, IATAcode, AYT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AYT
Context triple: [Antalya Airport, IATAcode, AYT]
  • A. AYT chosen
    AYT is the IATA airport code for Antalya Airport, a major international gateway serving the resort city of Antalya on Turkey’s Mediterranean coast.
  • B. AYQ
    AYQ is the IATA airport code for Ayers Rock (Connellan) Airport, which serves the Yulara resort area near Uluru in Australia’s Northern Territory.
  • C. Ayo
    Ayo is a 2014 studio album by Nigerian singer Wizkid that helped solidify his status as a leading figure in contemporary Afrobeats.
  • D. AY
    AY is the IATA airline designator assigned to Finnair, the flag carrier and largest airline of Finland.
  • E. Ay
    Ay was a short-reigning ancient Egyptian pharaoh of the late 18th Dynasty, known for succeeding Tutankhamun and ruling during the turbulent period following the Amarna era.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed93de98c8190ad838ce507b77c8a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af030114c88190b725908a32ace750 completed March 9, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589f5864881909c9fc787dd9b2341 completed March 14, 2026, 4:16 p.m.
Created at: March 9, 2026, 3:45 p.m.