Triple

T21294960
Position Surface form Disambiguated ID Type / Status
Subject Ko Un E524896 entity
Predicate nativeName P15 FINISHED
Object 고은
고은은 한국 현대시를 대표하는 시인이자 소설가로, 방대한 시집과 문학 작품을 통해 국내외에서 널리 알려진 문학가이다.
E1475715 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: 고은 | Statement: [Ko Un, nativeName, 고은]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 고은
Context triple: [Ko Un, nativeName, 고은]
  • A. Byeon Bong-seon
    Byeon Bong-seon is a South Korean cinematographer known for his work on the sci-fi film "Space Sweepers."
  • B. Jeong Seon
    Jeong Seon was a prominent Korean painter of the Joseon dynasty, renowned for pioneering a distinctive style of true-view landscape painting based on actual Korean scenery.
  • C. Myung-whun
    Myung-whun is a renowned South Korean conductor and pianist known for leading major international orchestras and promoting classical music worldwide.
  • D. Dong Hee-seon
    Dong Hee-seon is a South Korean screenwriter best known for her work on the hit fantasy-comedy film "Miss Granny."
  • E. Chae Song-hwa
    Chae Song-hwa is a highly skilled, compassionate neurosurgeon and one of the central members of the longtime friend group in the South Korean medical drama "Hospital Playlist."
  • 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: 고은
Triple: [Ko Un, nativeName, 고은]
Generated description
고은은 한국 현대시를 대표하는 시인이자 소설가로, 방대한 시집과 문학 작품을 통해 국내외에서 널리 알려진 문학가이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 고은
Target entity description: 고은은 한국 현대시를 대표하는 시인이자 소설가로, 방대한 시집과 문학 작품을 통해 국내외에서 널리 알려진 문학가이다.
  • A. Byeon Bong-seon
    Byeon Bong-seon is a South Korean cinematographer known for his work on the sci-fi film "Space Sweepers."
  • B. Jeong Seon
    Jeong Seon was a prominent Korean painter of the Joseon dynasty, renowned for pioneering a distinctive style of true-view landscape painting based on actual Korean scenery.
  • C. Myung-whun
    Myung-whun is a renowned South Korean conductor and pianist known for leading major international orchestras and promoting classical music worldwide.
  • D. Dong Hee-seon
    Dong Hee-seon is a South Korean screenwriter best known for her work on the hit fantasy-comedy film "Miss Granny."
  • E. Chae Song-hwa
    Chae Song-hwa is a highly skilled, compassionate neurosurgeon and one of the central members of the longtime friend group in the South Korean medical drama "Hospital Playlist."
  • 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73857784881908c3b8418a4c00c1e completed April 21, 2026, 8:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09981227a4819095b3ba894f0c6828 completed May 17, 2026, 10:27 a.m.
NEDg Description generation batch_6a099892435c8190844d6587d1202ff2 completed May 17, 2026, 10:29 a.m.
NED2 Entity disambiguation (via description) batch_6a0999266e0c8190b815cb90d9c984c6 completed May 17, 2026, 10:32 a.m.
Created at: April 16, 2026, 4:04 p.m.