Triple

T15180732
Position Surface form Disambiguated ID Type / Status
Subject Carros E362735 entity
Predicate mayor P185 FINISHED
Object Yannick Bernard
Yannick Bernard is a French local politician who serves as the mayor of the commune of Carros in southeastern France.
 E1141477 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: Yannick Bernard | Statement: [Carros, mayor, Yannick Bernard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yannick Bernard
Context triple: [Carros, mayor, Yannick Bernard]
  • A. Yannick Durand
    Yannick Durand is a person notable enough to be specifically cited as a bearer of the surname Durand.
  • B. Albert Dupontel
    Albert Dupontel is a French actor, screenwriter, and film director known for his darkly comic, inventive films such as "9 Month Stretch" and "Bye Bye Morons."
  • C. Emmanuel Bailly
    Emmanuel Bailly was a 19th-century French Catholic layman and journalist best known as the founding president and organizer of the Society of Saint Vincent de Paul.
  • D. Olivier Gacquerre
    Olivier Gacquerre is a French politician who serves as the mayor of the northern French city of Béthune.
  • E. Olivier Aubin-Mercier
    Olivier Aubin-Mercier is a Canadian mixed martial artist known for competing in major promotions such as the UFC and the Professional Fighters League (PFL), where he has been a lightweight standout.
  • 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: Yannick Bernard
Triple: [Carros, mayor, Yannick Bernard]
Generated description
Yannick Bernard is a French local politician who serves as the mayor of the commune of Carros in southeastern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yannick Bernard
Target entity description: Yannick Bernard is a French local politician who serves as the mayor of the commune of Carros in southeastern France.
  • A. Yannick Durand
    Yannick Durand is a person notable enough to be specifically cited as a bearer of the surname Durand.
  • B. Albert Dupontel
    Albert Dupontel is a French actor, screenwriter, and film director known for his darkly comic, inventive films such as "9 Month Stretch" and "Bye Bye Morons."
  • C. Emmanuel Bailly
    Emmanuel Bailly was a 19th-century French Catholic layman and journalist best known as the founding president and organizer of the Society of Saint Vincent de Paul.
  • D. Olivier Gacquerre
    Olivier Gacquerre is a French politician who serves as the mayor of the northern French city of Béthune.
  • E. Olivier Aubin-Mercier
    Olivier Aubin-Mercier is a Canadian mixed martial artist known for competing in major promotions such as the UFC and the Professional Fighters League (PFL), where he has been a lightweight standout.
  • 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_69d85a09a39c81908759f23268e2d408 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00664caac81909bee1268264769f8 completed April 15, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fec89210e081909e8077fa2487c40e completed May 9, 2026, 5:39 a.m.
NEDg Description generation batch_69fec998bd908190a14574b9e08cab4a completed May 9, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_69feca58c02081909b8ee4066297e194 completed May 9, 2026, 5:47 a.m.
Created at: April 10, 2026, 3:09 a.m.