Triple

T15180686
Position Surface form Disambiguated ID Type / Status
Subject Sospel E362734 entity
Predicate river P165 FINISHED
Object Bévéra
Bévéra is a river in southeastern France and northwestern Italy that flows through the Alpes-Maritimes before joining the Roya.
E1141472 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: Bévéra | Statement: [Sospel, river, Bévéra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bévéra
Context triple: [Sospel, river, Bévéra]
  • A. Pévèle
    Pévèle is a rural area in northern France known for its gently rolling farmland, small towns, and role as a traditional cobbled sector in the Paris–Roubaix cycling race.
  • B. Bevercé
    Bevercé is a village in the municipality of Malmedy in the province of Liège, in the French-speaking Walloon region of Belgium.
  • C. Vereya
    Vereya is a small historic town in Russia that was once part of the former Moscow Governorate.
  • D. Myrtha
    Myrtha is the powerful and vengeful Queen of the Wilis in the Romantic ballet "Giselle."
  • E. Bebra
    Bebra is a small settlement located in the historical region of Westphalia in western Germany.
  • 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: Bévéra
Triple: [Sospel, river, Bévéra]
Generated description
Bévéra is a river in southeastern France and northwestern Italy that flows through the Alpes-Maritimes before joining the Roya.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bévéra
Target entity description: Bévéra is a river in southeastern France and northwestern Italy that flows through the Alpes-Maritimes before joining the Roya.
  • A. Pévèle
    Pévèle is a rural area in northern France known for its gently rolling farmland, small towns, and role as a traditional cobbled sector in the Paris–Roubaix cycling race.
  • B. Bevercé
    Bevercé is a village in the municipality of Malmedy in the province of Liège, in the French-speaking Walloon region of Belgium.
  • C. Vereya
    Vereya is a small historic town in Russia that was once part of the former Moscow Governorate.
  • D. Myrtha
    Myrtha is the powerful and vengeful Queen of the Wilis in the Romantic ballet "Giselle."
  • E. Bebra
    Bebra is a small settlement located in the historical region of Westphalia in western Germany.
  • 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.