Triple

T20289722
Position Surface form Disambiguated ID Type / Status
Subject Jeonggwanheon Pavilion E509985 entity
Predicate hasNameInKorean P17869 FINISHED
Object 정관헌
정관헌은 서울 덕수궁 안에 위치한 대한제국 시기 서양식과 전통 양식이 혼합된 근대 건축물로, 고종이 다과를 즐기고 외교 사절을 접견하던 장소이다.
E1422734 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: 정관헌 | Statement: [Jeonggwanheon Pavilion, hasNameInKorean, 정관헌]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 정관헌
Context triple: [Jeonggwanheon Pavilion, hasNameInKorean, 정관헌]
  • A. Kim Seong-cheol
    Kim Seong-cheol is a South Korean television producer best known for his executive production work on the dark fantasy series "Hellbound."
  • B. Song Young-chang
    Song Young-chang is a South Korean actor known for his supporting roles in films and television dramas, often portraying authoritative or high-ranking characters.
  • C. Yi Myeong-bok
    Yi Myeong-bok was the birth name of Gojong, the 26th king of Joseon and first emperor of the Korean Empire.
  • D. 손기정
    손기정은 1936년 베를린 올림픽 마라톤에서 우승한 한국인 선수로, 일제강점기 조선인의 민족적 자긍심을 상징하는 인물이다.
  • E. Choe Si-hyeong
    Choe Si-hyeong was a prominent 19th-century Korean religious leader who guided and systematized the Donghak (Eastern Learning) movement after its founder’s death.
  • 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: 정관헌
Triple: [Jeonggwanheon Pavilion, hasNameInKorean, 정관헌]
Generated description
정관헌은 서울 덕수궁 안에 위치한 대한제국 시기 서양식과 전통 양식이 혼합된 근대 건축물로, 고종이 다과를 즐기고 외교 사절을 접견하던 장소이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 정관헌
Target entity description: 정관헌은 서울 덕수궁 안에 위치한 대한제국 시기 서양식과 전통 양식이 혼합된 근대 건축물로, 고종이 다과를 즐기고 외교 사절을 접견하던 장소이다.
  • A. Kim Seong-cheol
    Kim Seong-cheol is a South Korean television producer best known for his executive production work on the dark fantasy series "Hellbound."
  • B. Song Young-chang
    Song Young-chang is a South Korean actor known for his supporting roles in films and television dramas, often portraying authoritative or high-ranking characters.
  • C. Yi Myeong-bok
    Yi Myeong-bok was the birth name of Gojong, the 26th king of Joseon and first emperor of the Korean Empire.
  • D. 손기정
    손기정은 1936년 베를린 올림픽 마라톤에서 우승한 한국인 선수로, 일제강점기 조선인의 민족적 자긍심을 상징하는 인물이다.
  • E. Choe Si-hyeong
    Choe Si-hyeong was a prominent 19th-century Korean religious leader who guided and systematized the Donghak (Eastern Learning) movement after its founder’s death.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e67694d50881909d59c1037295c1d0 completed April 20, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a085a2da9d48190b4a1fd2c95b60093 completed May 16, 2026, 11:51 a.m.
NEDg Description generation batch_6a085aecd7e48190a82b7cc8ac9f53ba completed May 16, 2026, 11:54 a.m.
NED2 Entity disambiguation (via description) batch_6a085baddf1c8190ac7444a8e1d5128f completed May 16, 2026, 11:57 a.m.
Created at: April 16, 2026, 11:11 a.m.