Triple

T11339538
Position Surface form Disambiguated ID Type / Status
Subject Sung Kang E268557 entity
Predicate spouse P13 FINISHED
Object Miki Yim
Miki Yim is a Korean-American fashion professional known for her work in luxury retail and for being married to actor Sung Kang.
 E920381 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: Miki Yim | Statement: [Sung Kang, spouse, Miki Yim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Miki Yim
Context triple: [Sung Kang, spouse, Miki Yim]
  • A. Mia Yoo
    Mia Yoo is a theatre director and arts leader best known for heading New York’s influential La MaMa Experimental Theatre Club, where she champions innovative and international performance.
  • B. Miri Yoon
    Miri Yoon is a film producer known for her work on the psychological thriller "Don't Worry Darling."
  • C. Cheryl Song
    Cheryl Song is an American dancer and actress best known as a featured Soul Train dancer who also appeared in the 1988 action film "Action Jackson."
  • D. Nikki Chooi
    Nikki Chooi is a Canadian violinist acclaimed for his solo, chamber, and orchestral performances, including roles as concertmaster and ensemble member.
  • E. Candice Yu
    Candice Yu is a Hong Kong actress known for her work in 1970s and 1980s Cantonese cinema and television.
  • 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: Miki Yim
Triple: [Sung Kang, spouse, Miki Yim]
Generated description
Miki Yim is a Korean-American fashion professional known for her work in luxury retail and for being married to actor Sung Kang.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Miki Yim
Target entity description: Miki Yim is a Korean-American fashion professional known for her work in luxury retail and for being married to actor Sung Kang.
  • A. Mia Yoo
    Mia Yoo is a theatre director and arts leader best known for heading New York’s influential La MaMa Experimental Theatre Club, where she champions innovative and international performance.
  • B. Miri Yoon
    Miri Yoon is a film producer known for her work on the psychological thriller "Don't Worry Darling."
  • C. Cheryl Song
    Cheryl Song is an American dancer and actress best known as a featured Soul Train dancer who also appeared in the 1988 action film "Action Jackson."
  • D. Nikki Chooi
    Nikki Chooi is a Canadian violinist acclaimed for his solo, chamber, and orchestral performances, including roles as concertmaster and ensemble member.
  • E. Candice Yu
    Candice Yu is a Hong Kong actress known for her work in 1970s and 1980s Cantonese cinema and television.
  • 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_69d6aacb1f0881908c84a349fd1be047 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea01c6c08190910a6ce8fb7e186d completed April 9, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5433d3e848190ad4f51c23d5a8bb2 completed April 19, 2026, 9:03 p.m.
NEDg Description generation batch_69e5474aad3481909c1afb385cb5889b completed April 19, 2026, 9:21 p.m.
NED2 Entity disambiguation (via description) batch_69e54edb9ac08190a760de11857e791c completed April 19, 2026, 9:53 p.m.
Created at: April 8, 2026, 9:33 p.m.