Triple

T10597384
Position Surface form Disambiguated ID Type / Status
Subject Mary Duke Lyon E250150 entity
Predicate familyName P18 FINISHED
Object Duke
Duke is a prominent American family name historically associated with wealth, philanthropy, and the development of Duke University in North Carolina.
E567682 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: Duke | Statement: [Mary Duke Lyon, familyName, Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke
Context triple: [Mary Duke Lyon, familyName, Duke]
  • A. Duke
    Duke is the men's basketball team of Duke University, renowned as one of the most successful and storied programs in NCAA history.
  • B. Duke
    Duke is a prominent clan of the Efik people, historically influential in their social and political organization in southeastern Nigeria.
  • C. Duke
    Duke is a central G.I. Joe team leader portrayed by Channing Tatum in the action film "G.I. Joe: Retaliation."
  • D. Duke
    Duke is a large, shaggy brown rescue dog who becomes one of the central comedic protagonists in the animated film "The Secret Life of Pets."
  • E. Duke
    Duke is the famous nickname of American actor John Wayne, a legendary Hollywood star known for his roles in Westerns and war films.
  • 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: Duke
Triple: [Mary Duke Lyon, familyName, Duke]
Generated description
Duke is a prominent American family name historically associated with wealth, philanthropy, and the development of Duke University in North Carolina.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Duke
Target entity description: Duke is a prominent American family name historically associated with wealth, philanthropy, and the development of Duke University in North Carolina.
  • A. Duke chosen
    Duke is a prominent American family name most famously associated with the wealthy industrialist and philanthropic Duke family of North Carolina.
  • B. Duke
    Duke is a surname most prominently associated with David Duke, an American white supremacist and former Ku Klux Klan leader.
  • C. Duke
    Duke is the men's basketball team of Duke University, renowned as one of the most successful and storied programs in NCAA history.
  • D. Duke
    Duke is a private research university in Durham, North Carolina, renowned for its strong academic programs and competitive NCAA Division I athletics.
  • E. Duke
    Duke is the nickname of Duke Ellington, the influential American jazz composer, pianist, and bandleader who became a central figure in 20th-century music.
  • F. None of above.

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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d5278e5d5481908f4e19c52bd80327 completed April 7, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96b6109f08190915953e0ab708981 completed April 10, 2026, 9:28 p.m.
NEDg Description generation batch_69d96dee84f48190bf5b0cb1115a8bba completed April 10, 2026, 9:38 p.m.
NED2 Entity disambiguation (via description) batch_69d9708824208190acf75933962d690f completed April 10, 2026, 9:50 p.m.
Created at: April 6, 2026, 12:41 p.m.