Triple

T16886443
Position Surface form Disambiguated ID Type / Status
Subject Hung Yan-yan E421552 entity
Predicate givenName P17 FINISHED
Object Yan-yan
Yan-yan is the given name of Hung Yan-yan, a Hong Kong martial artist, actor, and action choreographer known for his work in kung fu and action cinema.
 E1238559 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: Yan-yan | Statement: [Hung Yan-yan, givenName, Yan-yan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yan-yan
Context triple: [Hung Yan-yan, givenName, Yan-yan]
  • A. Yan Yana
    Yan Yana is a notable literary work by Turkish poet and writer Melih Cevdet Anday.
  • B. Shanshan
    Shanshan was an ancient oasis kingdom in the eastern Tarim Basin, known for its role as a Silk Road crossroads and its mix of Indo-European and Chinese cultural influences.
  • C. Yuko
    Yuko is an alternate name for the Yukpa language, an indigenous language spoken by the Yukpa people of Colombia and Venezuela.
  • D. Yuko
    Yuko is a common Japanese feminine given name borne by numerous notable figures in fields such as entertainment, sports, and the arts.
  • E. Jingjing
    Jingjing is one of the five Fuwa mascots of the 2008 Beijing Summer Olympics, represented as a giant panda symbolizing happiness and prosperity.
  • 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: Yan-yan
Triple: [Hung Yan-yan, givenName, Yan-yan]
Generated description
Yan-yan is the given name of Hung Yan-yan, a Hong Kong martial artist, actor, and action choreographer known for his work in kung fu and action cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yan-yan
Target entity description: Yan-yan is the given name of Hung Yan-yan, a Hong Kong martial artist, actor, and action choreographer known for his work in kung fu and action cinema.
  • A. Yan Yana
    Yan Yana is a notable literary work by Turkish poet and writer Melih Cevdet Anday.
  • B. Shanshan
    Shanshan was an ancient oasis kingdom in the eastern Tarim Basin, known for its role as a Silk Road crossroads and its mix of Indo-European and Chinese cultural influences.
  • C. Yuko
    Yuko is an alternate name for the Yukpa language, an indigenous language spoken by the Yukpa people of Colombia and Venezuela.
  • D. Yuko
    Yuko is a common Japanese feminine given name borne by numerous notable figures in fields such as entertainment, sports, and the arts.
  • E. Jingjing
    Jingjing is one of the five Fuwa mascots of the 2008 Beijing Summer Olympics, represented as a giant panda symbolizing happiness and prosperity.
  • 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_69d889d470fc8190b4aec199636c0c56 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc126e881909dae8133ad34acc9 completed April 18, 2026, 5:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2bcf290819098be9def471e02b8 completed May 10, 2026, 5:39 p.m.
NEDg Description generation batch_6a00c3c25e9481908327bb6646212368 completed May 10, 2026, 5:43 p.m.
NED2 Entity disambiguation (via description) batch_6a00c44e37b48190a62b315ddbbd4ec4 completed May 10, 2026, 5:45 p.m.
Created at: April 10, 2026, 5:29 a.m.