Triple

T20387424
Position Surface form Disambiguated ID Type / Status
Subject Off Centre E497994 entity
Predicate hasCastMember P2308 FINISHED
Object Sung-Hi Lee
Sung-Hi Lee is a Korean-born American model and actress known for her work in magazines, films, and television.
E1433458 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: Sung-Hi Lee | Statement: [Off Centre, hasCastMember, Sung-Hi Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sung-Hi Lee
Context triple: [Off Centre, hasCastMember, Sung-Hi Lee]
  • A. Soo-Yung Han
    Soo-Yung Han is the young daughter of a Chinese consul whose kidnapping repeatedly drives the central plot and emotional stakes of the Rush Hour film series.
  • B. Wookyung Jung
    Wookyung Jung is a film producer best known for working on the animated feature "The Nut Job."
  • C. Jae-on Kim
    Jae-on Kim is a political scientist known for his work on democratic participation and political equality.
  • D. So-hee Kim
    So-hee Kim is a television producer best known for her executive production work on the historical sci-fi drama series "Project Blue Book."
  • E. Ji-Yoon Kim
    Ji-Yoon Kim is the beleaguered yet determined new chair of a struggling university English department in the Netflix dramedy "The Chair," juggling academic politics, cultural change, and single motherhood.
  • 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: Sung-Hi Lee
Triple: [Off Centre, hasCastMember, Sung-Hi Lee]
Generated description
Sung-Hi Lee is a Korean-born American model and actress known for her work in magazines, films, and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sung-Hi Lee
Target entity description: Sung-Hi Lee is a Korean-born American model and actress known for her work in magazines, films, and television.
  • A. Soo-Yung Han
    Soo-Yung Han is the young daughter of a Chinese consul whose kidnapping repeatedly drives the central plot and emotional stakes of the Rush Hour film series.
  • B. Wookyung Jung
    Wookyung Jung is a film producer best known for working on the animated feature "The Nut Job."
  • C. Jae-on Kim
    Jae-on Kim is a political scientist known for his work on democratic participation and political equality.
  • D. So-hee Kim
    So-hee Kim is a television producer best known for her executive production work on the historical sci-fi drama series "Project Blue Book."
  • E. Ji-Yoon Kim
    Ji-Yoon Kim is the beleaguered yet determined new chair of a struggling university English department in the Netflix dramedy "The Chair," juggling academic politics, cultural change, and single motherhood.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790c935881908f901d058e6a83a9 completed April 20, 2026, 7:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a088b0181a4819091030ed92f04d2dc completed May 16, 2026, 3:19 p.m.
NEDg Description generation batch_6a088f2c8ccc8190a1dc02db8e799355 completed May 16, 2026, 3:37 p.m.
NED2 Entity disambiguation (via description) batch_6a088f81fd0c8190a006db7e4fa9b440 completed May 16, 2026, 3:38 p.m.
Created at: April 16, 2026, 11:28 a.m.