Triple

T21869361
Position Surface form Disambiguated ID Type / Status
Subject Oldboy E539962 entity
Predicate mainCharacter P1183 FINISHED
Object Oh Dae-su
Oh Dae-su is the vengeful, psychologically tormented protagonist of the South Korean neo-noir thriller film "Oldboy."
E1505701 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: Oh Dae-su | Statement: [Oldboy, mainCharacter, Oh Dae-su]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oh Dae-su
Context triple: [Oldboy, mainCharacter, Oh Dae-su]
  • A. Woncheuk
    Woncheuk was a 7th-century Korean Buddhist monk and scholar renowned for his influential commentaries on Yogācāra and Huayan doctrines in Tang China.
  • B. Sung-tae
    Sung-tae is a Korean masculine given name commonly used in South Korea.
  • C. Yong-gi
    Yong-gi is a Korean given name commonly used for males.
  • D. 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.
  • E. Oh Man-seok
    Oh Man-seok is a South Korean actor and musical theatre performer known for his versatile roles on stage, television, and film.
  • 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: Oh Dae-su
Triple: [Oldboy, mainCharacter, Oh Dae-su]
Generated description
Oh Dae-su is the vengeful, psychologically tormented protagonist of the South Korean neo-noir thriller film "Oldboy."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Oh Dae-su
Target entity description: Oh Dae-su is the vengeful, psychologically tormented protagonist of the South Korean neo-noir thriller film "Oldboy."
  • A. Woncheuk
    Woncheuk was a 7th-century Korean Buddhist monk and scholar renowned for his influential commentaries on Yogācāra and Huayan doctrines in Tang China.
  • B. Sung-tae
    Sung-tae is a Korean masculine given name commonly used in South Korea.
  • C. Yong-gi
    Yong-gi is a Korean given name commonly used for males.
  • D. 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.
  • E. Oh Man-seok
    Oh Man-seok is a South Korean actor and musical theatre performer known for his versatile roles on stage, television, and film.
  • 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_6a0a4be1b1148190a3d787fbae00f802 completed May 17, 2026, 11:14 p.m.
NEDg Description generation batch_6a0a4c9aace88190a2006b3d0f13e3bf completed May 17, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_6a0a4cfff21081908f59cba1d8a1ac9d completed May 17, 2026, 11:19 p.m.
Created at: April 16, 2026, 6:57 p.m.