Triple

T9233703
Position Surface form Disambiguated ID Type / Status
Subject Marguerite Duras E221883 entity
Predicate familyName P18 FINISHED
Object Donnadieu
Donnadieu is the birth surname of the renowned French writer and filmmaker Marguerite Duras.
 E786186 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: Donnadieu | Statement: [Marguerite Duras, familyName, Donnadieu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Donnadieu
Context triple: [Marguerite Duras, familyName, Donnadieu]
  • A. Dalou
    Dalou is a French surname most notably associated with the 19th-century sculptor Jules Dalou, renowned for his realist public monuments.
  • B. Jodoigne
    Jodoigne is a historic town in Walloon Brabant, Belgium, known for its medieval architecture and role in regional agriculture.
  • C. Annaud
    Annaud is the surname of Jean-Jacques Annaud, a renowned French film director, screenwriter, and producer known for works such as "The Name of the Rose" and "The Bear."
  • D. Durgeon
    The Durgeon is a river in eastern France that flows through the town of Vesoul in the Haute-Saône department.
  • E. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • 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: Donnadieu
Triple: [Marguerite Duras, familyName, Donnadieu]
Generated description
Donnadieu is the birth surname of the renowned French writer and filmmaker Marguerite Duras.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Donnadieu
Target entity description: Donnadieu is the birth surname of the renowned French writer and filmmaker Marguerite Duras.
  • A. Dalou
    Dalou is a French surname most notably associated with the 19th-century sculptor Jules Dalou, renowned for his realist public monuments.
  • B. Jodoigne
    Jodoigne is a historic town in Walloon Brabant, Belgium, known for its medieval architecture and role in regional agriculture.
  • C. Annaud
    Annaud is the surname of Jean-Jacques Annaud, a renowned French film director, screenwriter, and producer known for works such as "The Name of the Rose" and "The Bear."
  • D. Durgeon
    The Durgeon is a river in eastern France that flows through the town of Vesoul in the Haute-Saône department.
  • E. Doncieux
    Doncieux is a French surname most notably associated with Camille Doncieux, the first wife and frequent model of painter Claude Monet.
  • 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_69ca83ed628c8190bc02d641e57f097f completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccee1baa3c8190870d1e850ccab1e0 completed April 1, 2026, 10:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077bb5b10819083fd2de3ed7d69a4 completed April 4, 2026, 2:30 a.m.
NEDg Description generation batch_69d079227348819083cc2c1bb36831f0 completed April 4, 2026, 2:36 a.m.
NED2 Entity disambiguation (via description) batch_69d07980eb1481909450ec1e6537587f completed April 4, 2026, 2:37 a.m.
Created at: March 30, 2026, 7:29 p.m.