Triple

T8262996
Position Surface form Disambiguated ID Type / Status
Subject Yokota Air Base E193236 entity
Predicate IATACode P418 FINISHED
Object OKO
OKO is the IATA airport code for Yokota Air Base, a United States Air Force installation in western Tokyo, Japan.
 E722228 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: OKO | Statement: [Yokota Air Base, IATACode, OKO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: OKO
Context triple: [Yokota Air Base, IATACode, OKO]
  • A. OKA
    OKA is the IATA airport code for Naha Airport, the main air gateway to Okinawa, Japan.
  • B. Okak
    Okak is a dialectal variety of the Fang language spoken by Fang communities in Central Africa.
  • C. Oh-OK
    Oh-OK was an early 1980s Athens, Georgia indie pop band known for its minimalist, off-kilter sound and for featuring future members of influential alternative acts.
  • D. EOK
    EOK is the Estonian Olympic Committee, the national body responsible for organizing Estonia’s participation in the Olympic Games and promoting Olympic sports in the country.
  • E. Oku
    Oku is a town and traditional kingdom in Cameroon's Northwest Region, known for its rich cultural heritage, mountainous landscape, and production of Oku white honey.
  • 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: OKO
Triple: [Yokota Air Base, IATACode, OKO]
Generated description
OKO is the IATA airport code for Yokota Air Base, a United States Air Force installation in western Tokyo, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: OKO
Target entity description: OKO is the IATA airport code for Yokota Air Base, a United States Air Force installation in western Tokyo, Japan.
  • A. OKA
    OKA is the IATA airport code for Naha Airport, the main air gateway to Okinawa, Japan.
  • B. Okak
    Okak is a dialectal variety of the Fang language spoken by Fang communities in Central Africa.
  • C. Oh-OK
    Oh-OK was an early 1980s Athens, Georgia indie pop band known for its minimalist, off-kilter sound and for featuring future members of influential alternative acts.
  • D. EOK
    EOK is the Estonian Olympic Committee, the national body responsible for organizing Estonia’s participation in the Olympic Games and promoting Olympic sports in the country.
  • E. Oku
    Oku is a town and traditional kingdom in Cameroon's Northwest Region, known for its rich cultural heritage, mountainous landscape, and production of Oku white honey.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb793991b481908ad7221405e88ab7 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd3573cee48190b72bdcdc433db93e completed April 1, 2026, 3:10 p.m.
NEDg Description generation batch_69cd37a7ea30819094b1c140868fab5f completed April 1, 2026, 3:20 p.m.
NED2 Entity disambiguation (via description) batch_69cd4f09a7a8819096ae509767ca61ee completed April 1, 2026, 4:59 p.m.
Created at: March 30, 2026, 5:49 p.m.