Triple

T2498574
Position Surface form Disambiguated ID Type / Status
Subject Asiana Airlines E52407 entity
Predicate operatesRoute P3695 FINISHED
Object Seoul–London
Seoul–London is an intercontinental air route connecting the capital cities of South Korea and the United Kingdom.
 E276692 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–London | Statement: [Asiana Airlines, operatesRoute, Seoul–London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Seoul–London
Context triple: [Asiana Airlines, operatesRoute, Seoul–London]
  • A. Seoul–Frankfurt
    Seoul–Frankfurt is an intercontinental air route linking South Korea’s capital with one of Germany’s major financial and transport hubs.
  • B. Seoul–New York
    Seoul–New York is a major intercontinental air route linking South Korea’s capital with the largest city in the United States.
  • C. 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.
  • D. London–Paris
    London–Paris is a major international rail route connecting the capitals of the United Kingdom and France via the Channel Tunnel.
  • E. Seoul–Los Angeles
    Seoul–Los Angeles is a major long-haul transpacific air route connecting South Korea’s capital with one of the largest cities on the U.S. West Coast.
  • 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–London
Triple: [Asiana Airlines, operatesRoute, Seoul–London]
Generated description
Seoul–London is an intercontinental air route connecting the capital cities of South Korea and the United Kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Seoul–London
Target entity description: Seoul–London is an intercontinental air route connecting the capital cities of South Korea and the United Kingdom.
  • A. Seoul–Frankfurt
    Seoul–Frankfurt is an intercontinental air route linking South Korea’s capital with one of Germany’s major financial and transport hubs.
  • B. Seoul–New York
    Seoul–New York is a major intercontinental air route linking South Korea’s capital with the largest city in the United States.
  • C. 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.
  • D. London–Paris
    London–Paris is a major international rail route connecting the capitals of the United Kingdom and France via the Channel Tunnel.
  • E. Seoul–Los Angeles
    Seoul–Los Angeles is a major long-haul transpacific air route connecting South Korea’s capital with one of the largest cities on the U.S. West Coast.
  • 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_69af5ce4dc2c8190a1327794ac1d1b15 completed March 9, 2026, 11:51 p.m.
NEDg Description generation batch_69af5dd89fe48190a99b2bea591818cd completed March 9, 2026, 11:55 p.m.
NED2 Entity disambiguation (via description) batch_69af5e8583408190862ba4e13bf81cbd completed March 9, 2026, 11:57 p.m.
Created at: March 6, 2026, 9:46 p.m.