Triple

T11200352
Position Surface form Disambiguated ID Type / Status
Subject Jean-Pierre Léaud E265022 entity
Predicate familyName P18 FINISHED
Object Léaud
Léaud is the surname of Jean-Pierre Léaud, the iconic French New Wave actor best known for his recurring role as Antoine Doinel in François Truffaut’s films.
E911674 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: Léaud | Statement: [Jean-Pierre Léaud, familyName, Léaud]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Léaud
Context triple: [Jean-Pierre Léaud, familyName, Léaud]
  • A. Lebrun
    Lebrun is a French surname borne by various notable figures in politics, arts, and other fields.
  • B. Gérard
    Gérard is a French given name, equivalent to the Germanic name Gerhard, commonly used in French-speaking countries.
  • C. Tanguy
    Tanguy is a French surname most notably associated with Yves Tanguy, a prominent 20th-century Surrealist painter.
  • D. Hervé
    Hervé is a French given name, often considered a variant of the English name Harvey, and is commonly used for males in French-speaking regions.
  • E. Lucé
    Lucé is a suburban commune in northern France, located near the city of Chartres in the Eure-et-Loir department.
  • 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: Léaud
Triple: [Jean-Pierre Léaud, familyName, Léaud]
Generated description
Léaud is the surname of Jean-Pierre Léaud, the iconic French New Wave actor best known for his recurring role as Antoine Doinel in François Truffaut’s films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Léaud
Target entity description: Léaud is the surname of Jean-Pierre Léaud, the iconic French New Wave actor best known for his recurring role as Antoine Doinel in François Truffaut’s films.
  • A. Lebrun
    Lebrun is a French surname borne by various notable figures in politics, arts, and other fields.
  • B. Gérard
    Gérard is a French given name, equivalent to the Germanic name Gerhard, commonly used in French-speaking countries.
  • C. Tanguy
    Tanguy is a French surname most notably associated with Yves Tanguy, a prominent 20th-century Surrealist painter.
  • D. Hervé
    Hervé is a French given name, often considered a variant of the English name Harvey, and is commonly used for males in French-speaking regions.
  • E. Lucé
    Lucé is a suburban commune in northern France, located near the city of Chartres in the Eure-et-Loir department.
  • 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_69d6aa9eb9248190b20211772621b4bc completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8c1e9f88190b2b42326aba9d778 completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4970df7cc81909c3b07ead58513e8 completed April 19, 2026, 8:49 a.m.
NEDg Description generation batch_69e49c09844881908e0d95ba3f239024 completed April 19, 2026, 9:10 a.m.
NED2 Entity disambiguation (via description) batch_69e49e7f8b108190bb69f532adf25809 completed April 19, 2026, 9:21 a.m.
Created at: April 8, 2026, 9:29 p.m.