Triple

T848974
Position Surface form Disambiguated ID Type / Status
Subject GPT-2 E18339 entity
Predicate paperAuthors P2002 FINISHED
Object Jeff Wu
Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
 E104412 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: Jeff Wu | Statement: [GPT-2, paperAuthors, Jeff Wu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jeff Wu
Context triple: [GPT-2, paperAuthors, Jeff Wu]
  • A. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • B. Tony Wu
    Tony Wu is a member of the technical team at xAI, the artificial intelligence company founded by Elon Musk.
  • C. Michael Chan
    Michael Chan is a common personal name shared by multiple individuals across fields such as politics, business, and entertainment.
  • D. Tom Wu
    Tom Wu is a British actor and martial artist known for his roles in action and crime films and television series.
  • E. 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."
  • 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: Jeff Wu
Triple: [GPT-2, paperAuthors, Jeff Wu]
Generated description
Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jeff Wu
Target entity description: Jeff Wu is a machine learning researcher known for his work on large language models, including co-authoring the original GPT-2 paper at OpenAI.
  • A. John Cheng
    John Cheng is a film producer best known for his work on the dark comedy movie "Horrible Bosses."
  • B. Tony Wu
    Tony Wu is a member of the technical team at xAI, the artificial intelligence company founded by Elon Musk.
  • C. Michael Chan
    Michael Chan is a common personal name shared by multiple individuals across fields such as politics, business, and entertainment.
  • D. Tom Wu
    Tom Wu is a British actor and martial artist known for his roles in action and crime films and television series.
  • E. 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."
  • 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_69a7b8472f188190b470893c76b20ccf completed March 4, 2026, 4:42 a.m.
NEDg Description generation batch_69a7bc1acf708190aa86cd5eca101966 completed March 4, 2026, 4:59 a.m.
NED2 Entity disambiguation (via description) batch_69a7bc96dd2881909310147292b99023 completed March 4, 2026, 5:01 a.m.
Created at: March 1, 2026, 7:38 p.m.