Triple

T17069895
Position Surface form Disambiguated ID Type / Status
Subject Mulan (2020 film) E414187 entity
Predicate castMember P1668 FINISHED
Object Jun Yu
Jun Yu is an actor known for his role in Disney's live-action adaptation of "Mulan" (2020).
E1251934 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: Jun Yu | Statement: [Mulan (2020 film), castMember, Jun Yu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jun Yu
Context triple: [Mulan (2020 film), castMember, Jun Yu]
  • A. Xiong Yi
    Xiong Yi was the legendary early ruler credited with establishing the ancient Chinese state of Chu during the Zhou dynasty.
  • B. Jin Yunpeng
    Jin Yunpeng was an early 20th-century Chinese military and political figure who twice served as premier during the turbulent warlord era of the Republic of China.
  • C. Yao Yecheng
    Yao Yecheng was the adoptive mother of Chiang Wei-kuo, the son of Chinese Nationalist leader Chiang Kai-shek.
  • D. Li Jiajun
    Li Jiajun is a Chinese short track speed skater who was one of the sport’s leading competitors in the late 1990s and early 2000s, winning multiple Olympic and World Championship medals.
  • E. Lin Yipeng
    Lin Yipeng is the birth name of Justin Lin, a Taiwanese-American film director best known for his work on the Fast & Furious franchise.
  • 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: Jun Yu
Triple: [Mulan (2020 film), castMember, Jun Yu]
Generated description
Jun Yu is an actor known for his role in Disney's live-action adaptation of "Mulan" (2020).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jun Yu
Target entity description: Jun Yu is an actor known for his role in Disney's live-action adaptation of "Mulan" (2020).
  • A. Xiong Yi
    Xiong Yi was the legendary early ruler credited with establishing the ancient Chinese state of Chu during the Zhou dynasty.
  • B. Jin Yunpeng
    Jin Yunpeng was an early 20th-century Chinese military and political figure who twice served as premier during the turbulent warlord era of the Republic of China.
  • C. Yao Yecheng
    Yao Yecheng was the adoptive mother of Chiang Wei-kuo, the son of Chinese Nationalist leader Chiang Kai-shek.
  • D. Li Jiajun
    Li Jiajun is a Chinese short track speed skater who was one of the sport’s leading competitors in the late 1990s and early 2000s, winning multiple Olympic and World Championship medals.
  • E. Lin Yipeng
    Lin Yipeng is the birth name of Justin Lin, a Taiwanese-American film director best known for his work on the Fast & Furious franchise.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbbfb1f08190807301ff6e573cf5 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a014140722481909f976e32597a873d completed May 11, 2026, 2:38 a.m.
NEDg Description generation batch_6a0141cadb6c8190b2832e12fd431b0b completed May 11, 2026, 2:41 a.m.
NED2 Entity disambiguation (via description) batch_6a014264ff8881909722c262c3f85e1f completed May 11, 2026, 2:43 a.m.
Created at: April 10, 2026, 5:34 a.m.