Triple

T5693590
Position Surface form Disambiguated ID Type / Status
Subject The Wedding Banquet E125482 entity
Predicate screenwriter P2831 FINISHED
Object Neil Peng
Neil Peng is a Taiwanese screenwriter best known for co-writing Ang Lee’s acclaimed film "The Wedding Banquet."
E539310 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: Neil Peng | Statement: [The Wedding Banquet, screenwriter, Neil Peng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Neil Peng
Context triple: [The Wedding Banquet, screenwriter, Neil Peng]
  • A. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • B. Sean Chen
    Sean Chen is a Taiwanese politician and technocrat who served as Premier of the Republic of China (Taiwan) in the early 2010s, known for his background in finance and economic policy.
  • C. William Wang
    William Wang is a Taiwanese-American entrepreneur best known as the founder and longtime CEO of the consumer electronics company Vizio.
  • D. Eddie Peng
    Eddie Peng is a Taiwanese-Canadian actor and singer known for his roles in Chinese-language action and historical films.
  • E. Jonathan Wang
    Jonathan Wang is a film producer best known for his work on the acclaimed, genre-bending movie "Everything Everywhere All at Once."
  • 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: Neil Peng
Triple: [The Wedding Banquet, screenwriter, Neil Peng]
Generated description
Neil Peng is a Taiwanese screenwriter best known for co-writing Ang Lee’s acclaimed film "The Wedding Banquet."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Neil Peng
Target entity description: Neil Peng is a Taiwanese screenwriter best known for co-writing Ang Lee’s acclaimed film "The Wedding Banquet."
  • A. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • B. Sean Chen
    Sean Chen is a Taiwanese politician and technocrat who served as Premier of the Republic of China (Taiwan) in the early 2010s, known for his background in finance and economic policy.
  • C. William Wang
    William Wang is a Taiwanese-American entrepreneur best known as the founder and longtime CEO of the consumer electronics company Vizio.
  • D. Eddie Peng
    Eddie Peng is a Taiwanese-Canadian actor and singer known for his roles in Chinese-language action and historical films.
  • E. Jonathan Wang
    Jonathan Wang is a film producer best known for his work on the acclaimed, genre-bending movie "Everything Everywhere All at Once."
  • 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_69c0082bb19c8190823a4facd3cba79b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023e7dbe48190850b501f223614e3 completed March 22, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a4f2bfc8190bc56c094f9ae9ce1 completed March 22, 2026, 9:08 p.m.
NEDg Description generation batch_69c05bb76a748190a3b1a289dbd92dee completed March 22, 2026, 9:14 p.m.
NED2 Entity disambiguation (via description) batch_69c05c498c4c8190bfa3ac17fba2b152 completed March 22, 2026, 9:16 p.m.
Created at: March 22, 2026, 3:44 p.m.