Triple

T2498576
Position Surface form Disambiguated ID Type / Status
Subject Asiana Airlines E52407 entity
Predicate operatesRoute P3695 FINISHED
Object Seoul–Tokyo
Seoul–Tokyo is a major international air route connecting the capitals of South Korea and Japan, serving as a key corridor for business and tourism between the two countries.
 E273268 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: Seoul–Tokyo | Statement: [Asiana Airlines, operatesRoute, Seoul–Tokyo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Seoul–Tokyo
Context triple: [Asiana Airlines, operatesRoute, Seoul–Tokyo]
  • A. Taipei–Tokyo
    Taipei–Tokyo is a major East Asian air route connecting the capital of Taiwan with Japan’s largest metropolitan area, served by numerous carriers and popular for both business and tourism travel.
  • B. Manila–Tokyo
    Manila–Tokyo is an international air route connecting the capital of the Philippines with the capital of Japan.
  • C. Tokyo
    Tokyo is Japan’s largest metropolis and a global center of finance, culture, technology, and transportation.
  • D. Yokohama
    Yokohama is Japan’s second-largest city and a major international port located just south of Tokyo.
  • E. Seoul
    Seoul is the capital and largest metropolis of South Korea, known as a major global center for technology, culture, and finance.
  • 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: Seoul–Tokyo
Triple: [Asiana Airlines, operatesRoute, Seoul–Tokyo]
Generated description
Seoul–Tokyo is a major international air route connecting the capitals of South Korea and Japan, serving as a key corridor for business and tourism between the two countries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Seoul–Tokyo
Target entity description: Seoul–Tokyo is a major international air route connecting the capitals of South Korea and Japan, serving as a key corridor for business and tourism between the two countries.
  • A. Taipei–Tokyo
    Taipei–Tokyo is a major East Asian air route connecting the capital of Taiwan with Japan’s largest metropolitan area, served by numerous carriers and popular for both business and tourism travel.
  • B. Manila–Tokyo
    Manila–Tokyo is an international air route connecting the capital of the Philippines with the capital of Japan.
  • C. Tokyo
    Tokyo is Japan’s largest metropolis and a global center of finance, culture, technology, and transportation.
  • D. Yokohama
    Yokohama is Japan’s second-largest city and a major international port located just south of Tokyo.
  • E. Seoul
    Seoul is the capital and largest metropolis of South Korea, known as a major global center for technology, culture, and finance.
  • 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_69ab4957b3a88190adf968ae0c1b931c completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1ae9040819091b3ca5b98659e99 completed March 7, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f9ed13c81909856db636bfb2e9e completed March 9, 2026, 7:29 p.m.
NEDg Description generation batch_69af23a305a48190b457b1b66779b90d completed March 9, 2026, 7:46 p.m.
NED2 Entity disambiguation (via description) batch_69af240855848190947190a662745b77 completed March 9, 2026, 7:48 p.m.
Created at: March 6, 2026, 9:46 p.m.