Triple

T848976
Position Surface form Disambiguated ID Type / Status
Subject GPT-2 E18339 entity
Predicate paperAuthors P2002 FINISHED
Object David Luan
David Luan is an AI researcher and entrepreneur known for his work on large language models at OpenAI and as co-founder and CEO of Adept AI.
 E105375 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: David Luan | Statement: [GPT-2, paperAuthors, David Luan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: David Luan
Context triple: [GPT-2, paperAuthors, David Luan]
  • A. Victor Wong
    Victor Wong was an American character actor known for his distinctive presence in films such as "The Last Emperor," "Big Trouble in Little China," and "Tremors."
  • B. Jason Wong
    Jason Wong is a British actor known for his roles in film and television, including his appearance in Guy Ritchie's crime-comedy series "The Gentlemen."
  • C. Daren Tang
    Daren Tang is a Singaporean lawyer and intellectual property expert who serves as the Director General of the World Intellectual Property Organization (WIPO).
  • D. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • E. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • 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: David Luan
Triple: [GPT-2, paperAuthors, David Luan]
Generated description
David Luan is an AI researcher and entrepreneur known for his work on large language models at OpenAI and as co-founder and CEO of Adept AI.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: David Luan
Target entity description: David Luan is an AI researcher and entrepreneur known for his work on large language models at OpenAI and as co-founder and CEO of Adept AI.
  • A. Victor Wong
    Victor Wong was an American character actor known for his distinctive presence in films such as "The Last Emperor," "Big Trouble in Little China," and "Tremors."
  • B. Jason Wong
    Jason Wong is a British actor known for his roles in film and television, including his appearance in Guy Ritchie's crime-comedy series "The Gentlemen."
  • C. Daren Tang
    Daren Tang is a Singaporean lawyer and intellectual property expert who serves as the Director General of the World Intellectual Property Organization (WIPO).
  • D. Kenneth Hsu
    Kenneth Hsu is a Swiss geologist and oceanographer known for his influential work on marine geology and the Messinian salinity crisis.
  • E. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • 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_69a4938b04208190b82e1df6b572c548 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b2b66c908190a52f731119b77a1e completed March 1, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c016a8a88190965e7c703b0329fb completed March 4, 2026, 5:16 a.m.
NEDg Description generation batch_69a7c1782d108190825ece29e7532bf6 completed March 4, 2026, 5:22 a.m.
NED2 Entity disambiguation (via description) batch_69a7c21dd42881908ac19fed7454d7a9 completed March 4, 2026, 5:24 a.m.
Created at: March 1, 2026, 7:38 p.m.