Triple

T21869474
Position Surface form Disambiguated ID Type / Status
Subject Train to Busan E539964 entity
Predicate mainCharacter P1183 FINISHED
Object Yon-suk
Yon-suk is the selfish and antagonistic businessman in the South Korean zombie film "Train to Busan," known for endangering others to save himself.
E1514319 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: Yon-suk | Statement: [Train to Busan, mainCharacter, Yon-suk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yon-suk
Context triple: [Train to Busan, mainCharacter, Yon-suk]
  • A. Yong-taek
    Yong-taek is a Korean masculine given name commonly used in South Korea.
  • B. Yong-gi
    Yong-gi is a Korean given name commonly used for males.
  • C. Yong-il
    Yong-il is a Korean masculine given name that can be shared by various individuals, including notable figures such as politicians and public officials.
  • D. Seonghwan
    Seonghwan is a locality in South Korea historically noted as the site of the Battle of Seonghwan during the First Sino-Japanese War.
  • E. Dong-soo
    Dong-soo is a central character in the South Korean film "Broker," portrayed as a morally conflicted man involved in an illegal baby adoption scheme.
  • 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: Yon-suk
Triple: [Train to Busan, mainCharacter, Yon-suk]
Generated description
Yon-suk is the selfish and antagonistic businessman in the South Korean zombie film "Train to Busan," known for endangering others to save himself.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yon-suk
Target entity description: Yon-suk is the selfish and antagonistic businessman in the South Korean zombie film "Train to Busan," known for endangering others to save himself.
  • A. Yong-taek
    Yong-taek is a Korean masculine given name commonly used in South Korea.
  • B. Yong-gi
    Yong-gi is a Korean given name commonly used for males.
  • C. Yong-il
    Yong-il is a Korean masculine given name that can be shared by various individuals, including notable figures such as politicians and public officials.
  • D. Seonghwan
    Seonghwan is a locality in South Korea historically noted as the site of the Battle of Seonghwan during the First Sino-Japanese War.
  • E. Dong-soo
    Dong-soo is a central character in the South Korean film "Broker," portrayed as a morally conflicted man involved in an illegal baby adoption scheme.
  • 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_69e0c478f59081909d54302b57fc1ce3 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0f334362c819094af465ee57b47e6 completed April 28, 2026, 5:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a7361a24081908b1334e2ad9923f9 completed May 18, 2026, 2:03 a.m.
NEDg Description generation batch_6a0a780f0c008190bd56b7af0bebbc85 completed May 18, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_6a0a78c2a94c8190841463b0a52ba16e completed May 18, 2026, 2:26 a.m.
Created at: April 16, 2026, 6:57 p.m.