Triple

T33466553
Position Surface form Disambiguated ID Type / Status
Subject 연상엽 E857061 entity
Predicate 한국이름 P17869 FINISHED
Object 스티븐 연
스티븐 연은 미국 드라마 「워킹 데드」와 영화 「미나리」 등으로 세계적인 인지도를 얻은 한국계 미국인 배우이다.
 E2051529 NE FINISHED

How this triple was built (3 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: 스티븐 연 | Statement: [연상엽, 한국이름, 스티븐 연]
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: 스티븐 연
Triple: [연상엽, 한국이름, 스티븐 연]
Generated description
스티븐 연은 미국 드라마 「워킹 데드」와 영화 「미나리」 등으로 세계적인 인지도를 얻은 한국계 미국인 배우이다.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: 한국이름
Context triple: [연상엽, 한국이름, 스티븐 연]
  • A. nameInKorean chosen
    Indicates that an entity’s name is expressed in the Korean language.
  • B. languageOfKoreanName
    Indicates that the specified language is the language in which the given Korean name is expressed or written.
  • C. hangulNameRomanized
    Indicates that an entity’s Korean Hangul name is represented in its romanized (Latin alphabet) form.
  • D. hanjaName
    Indicates that one entity is the Sino-Korean (hanja) written form corresponding to the name of another entity.
  • E. hangulProjectCountry
    Indicates that a country is associated with or involved in a Hangul-related project.
  • F. None of above.

Provenance (6 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_69f34973461481909c701c98ebd75623 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6e4fa60fc819088d51ef48d43447b completed May 3, 2026, 6:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a35816f3eb88190891e51f079d5fcae completed June 19, 2026, 5:50 p.m.
NEDg Description generation batch_6a3581f170bc8190a4df3412be7d01a7 completed June 19, 2026, 5:52 p.m.
NED2 Entity disambiguation (via description) batch_6a35845b7d148190af2e20a1b0c092aa completed June 19, 2026, 6:03 p.m.
PD Predicate disambiguation batch_69f6e3da41948190a4cfe866ce184f73 completed May 3, 2026, 5:57 a.m.
Created at: May 1, 2026, 1:37 a.m.