Triple

T22555491
Position Surface form Disambiguated ID Type / Status
Subject Yeon Sang-ho E557669 entity
Predicate nativeName P15 FINISHED
Object 연상호
연상호는 애니메이션 영화 〈돼지의 왕〉과 좀비 영화 〈부산행〉으로 널리 알려진 대한민국의 영화 감독이자 시나리오 작가이다.
 E1543381 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: 연상호 | Statement: [Yeon Sang-ho, nativeName, 연상호]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 연상호
Context triple: [Yeon Sang-ho, nativeName, 연상호]
  • A. 연상엽
    연상엽은 미국 드라마 ‘워킹 데드’와 영화 ‘미나리’, ‘노프’ 등으로 잘 알려진 한국계 미국인 배우 스티븐 연의 한국 이름이다.
  • B. An Chang-ho
    An Chang-ho was a prominent Korean independence activist, educator, and nationalist leader who played a key role in shaping modern Korean identity and reform movements in the early 20th century.
  • C. Jeong Won-oh
    Jeong Won-oh is a South Korean politician who serves as the mayor of Seoul's Seongdong District.
  • D. Moon Sung-keun
    Moon Sung-keun is a South Korean actor and former politician known for his roles in socially conscious films and television dramas.
  • E. Jeong Hyeong-don
    Jeong Hyeong-don is a South Korean comedian and television host best known for his work on popular variety shows such as "Infinite Challenge" and "Weekly Idol."
  • 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: 연상호
Triple: [Yeon Sang-ho, nativeName, 연상호]
Generated description
연상호는 애니메이션 영화 〈돼지의 왕〉과 좀비 영화 〈부산행〉으로 널리 알려진 대한민국의 영화 감독이자 시나리오 작가이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 연상호
Target entity description: 연상호는 애니메이션 영화 〈돼지의 왕〉과 좀비 영화 〈부산행〉으로 널리 알려진 대한민국의 영화 감독이자 시나리오 작가이다.
  • A. 연상엽
    연상엽은 미국 드라마 ‘워킹 데드’와 영화 ‘미나리’, ‘노프’ 등으로 잘 알려진 한국계 미국인 배우 스티븐 연의 한국 이름이다.
  • B. An Chang-ho
    An Chang-ho was a prominent Korean independence activist, educator, and nationalist leader who played a key role in shaping modern Korean identity and reform movements in the early 20th century.
  • C. Jeong Won-oh
    Jeong Won-oh is a South Korean politician who serves as the mayor of Seoul's Seongdong District.
  • D. Moon Sung-keun
    Moon Sung-keun is a South Korean actor and former politician known for his roles in socially conscious films and television dramas.
  • E. Jeong Hyeong-don
    Jeong Hyeong-don is a South Korean comedian and television host best known for his work on popular variety shows such as "Infinite Challenge" and "Weekly Idol."
  • 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_69e11e59db848190b4272ecd2b690ffd completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f78d8288190871d54db0a7f454b completed April 29, 2026, 1:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b2d6700548190aa5be562944ee8fd completed May 18, 2026, 3:16 p.m.
NEDg Description generation batch_6a0b364718308190937c3b7ae90ea9df completed May 18, 2026, 3:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0b37a1ecc08190ac89e862582833a0 completed May 18, 2026, 4 p.m.
Created at: April 16, 2026, 8:52 p.m.