Triple

T10475185
Position Surface form Disambiguated ID Type / Status
Subject House of Deréon E247025 entity
Predicate namedAfter P63 FINISHED
Object Agnèz Deréon
Agnèz Deréon was the maternal grandmother of Beyoncé and the family matriarch whose legacy inspired the name of the fashion brand House of Deréon.
 E864734 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: Agnèz Deréon | Statement: [House of Deréon, namedAfter, Agnèz Deréon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Agnèz Deréon
Context triple: [House of Deréon, namedAfter, Agnèz Deréon]
  • A. Suzanne Darlan
    Suzanne Darlan was the wife of French admiral and Vichy leader François Darlan and a member of the French social elite during the early 20th century.
  • B. Karin Argoud
    Karin Argoud is an American actress best known for her role as Sonja Harper on the television sitcom "Mama’s Family."
  • C. Doro Merande
    Doro Merande was an American character actress known for her distinctive comic and eccentric roles in mid-20th-century film, television, and theater.
  • D. Catherine Brelet
    Catherine Brelet is a French film producer best known as the wife and longtime collaborator of acclaimed Swedish actor Max von Sydow.
  • E. Anny Danché
    Anny Danché is a human editor, likely involved in preparing, revising, or curating written or published materials.
  • 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: Agnèz Deréon
Triple: [House of Deréon, namedAfter, Agnèz Deréon]
Generated description
Agnèz Deréon was the maternal grandmother of Beyoncé and the family matriarch whose legacy inspired the name of the fashion brand House of Deréon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Agnèz Deréon
Target entity description: Agnèz Deréon was the maternal grandmother of Beyoncé and the family matriarch whose legacy inspired the name of the fashion brand House of Deréon.
  • A. Suzanne Darlan
    Suzanne Darlan was the wife of French admiral and Vichy leader François Darlan and a member of the French social elite during the early 20th century.
  • B. Karin Argoud
    Karin Argoud is an American actress best known for her role as Sonja Harper on the television sitcom "Mama’s Family."
  • C. Doro Merande
    Doro Merande was an American character actress known for her distinctive comic and eccentric roles in mid-20th-century film, television, and theater.
  • D. Catherine Brelet
    Catherine Brelet is a French film producer best known as the wife and longtime collaborator of acclaimed Swedish actor Max von Sydow.
  • E. Anny Danché
    Anny Danché is a human editor, likely involved in preparing, revising, or curating written or published materials.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5094f6b408190a5a26b1a82e4a02b completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8a0140f4c81908ce95b28e09cb04b completed April 10, 2026, 7 a.m.
NEDg Description generation batch_69d8a166404881909c28141fefea2936 completed April 10, 2026, 7:06 a.m.
NED2 Entity disambiguation (via description) batch_69d8a2c550ac81908444c6abfe14698a completed April 10, 2026, 7:12 a.m.
Created at: April 6, 2026, 12:21 p.m.