Triple

T10799129
Position Surface form Disambiguated ID Type / Status
Subject Washington Duke E254790 entity
Predicate child P120 FINISHED
Object Brody Duke
Brody Duke was an American tobacco industrialist and member of the prominent Duke family that helped shape the tobacco industry in the late 19th century.
E886459 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: Brody Duke | Statement: [Washington Duke, child, Brody Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brody Duke
Context triple: [Washington Duke, child, Brody Duke]
  • A. Brody
    Brody is a surname of English and Irish origin borne by various notable individuals across fields such as entertainment, sports, and public life.
  • B. Gage Creed
    Gage Creed is a young boy whose tragic death and supernatural resurrection drive the central horror and emotional conflict in Stephen King’s novel "Pet Sematary."
  • C. Brody Bruce
    Brody Bruce is a comic book–obsessed slacker and central character from Kevin Smith’s film "Mallrats," known for his sarcastic wit and pop-culture rants.
  • D. Caspian Vaughn
    Caspian Vaughn is a son of German supermodel and actress Claudia Schiffer.
  • E. Alec Hardison
    Alec Hardison is a brilliant, pop-culture-savvy hacker and tech expert who handles all things digital and logistical for the Leverage crew.
  • 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: Brody Duke
Triple: [Washington Duke, child, Brody Duke]
Generated description
Brody Duke was an American tobacco industrialist and member of the prominent Duke family that helped shape the tobacco industry in the late 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brody Duke
Target entity description: Brody Duke was an American tobacco industrialist and member of the prominent Duke family that helped shape the tobacco industry in the late 19th century.
  • A. Brody
    Brody is a surname of English and Irish origin borne by various notable individuals across fields such as entertainment, sports, and public life.
  • B. Gage Creed
    Gage Creed is a young boy whose tragic death and supernatural resurrection drive the central horror and emotional conflict in Stephen King’s novel "Pet Sematary."
  • C. Brody Bruce
    Brody Bruce is a comic book–obsessed slacker and central character from Kevin Smith’s film "Mallrats," known for his sarcastic wit and pop-culture rants.
  • D. Caspian Vaughn
    Caspian Vaughn is a son of German supermodel and actress Claudia Schiffer.
  • E. Alec Hardison
    Alec Hardison is a brilliant, pop-culture-savvy hacker and tech expert who handles all things digital and logistical for the Leverage crew.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d73334feb08190aae967eaa37659f7 completed April 9, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69de566352608190ab15e3a4b690c9a5 completed April 14, 2026, 2:59 p.m.
NEDg Description generation batch_69de5eaf3cc08190935cb6ddf2020166 completed April 14, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_69de63a902f4819089845bc6d7469c6b completed April 14, 2026, 3:56 p.m.
Created at: April 8, 2026, 9:17 p.m.