Triple

T20181427
Position Surface form Disambiguated ID Type / Status
Subject Val d’Ayas E492735 entity
Predicate hasRiver P165 FINISHED
Object Évançon
Évançon is a mountain river in Italy’s Aosta Valley that flows through the Val d’Ayas before joining the Dora Baltea.
 E1506120 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: Évançon | Statement: [Val d’Ayas, hasRiver, Évançon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Évançon
Context triple: [Val d’Ayas, hasRiver, Évançon]
  • A. Vaujours
    Vaujours is a small suburban commune in the northeastern outskirts of Paris, France.
  • B. Calvé
    Calvé is a well-known food brand, particularly recognized for its peanut butter and sauces, that forms part of Unilever’s global brand portfolio.
  • C. Ermontoise
    Ermontoise is the French demonym referring to a female inhabitant or native of the town of Ermont in France.
  • D. Brière
    Brière is a French-language surname most prominently associated with former NHL player and current hockey executive Daniel Brière.
  • E. Ferrière
    Ferrière is a French-language surname of Swiss origin borne by various notable individuals, including social worker and humanitarian Suzanne Ferrière.
  • 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: Évançon
Triple: [Val d’Ayas, hasRiver, Évançon]
Generated description
Évançon is a mountain river in Italy’s Aosta Valley that flows through the Val d’Ayas before joining the Dora Baltea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Évançon
Target entity description: Évançon is a mountain river in Italy’s Aosta Valley that flows through the Val d’Ayas before joining the Dora Baltea.
  • A. Vaujours
    Vaujours is a small suburban commune in the northeastern outskirts of Paris, France.
  • B. Calvé
    Calvé is a well-known food brand, particularly recognized for its peanut butter and sauces, that forms part of Unilever’s global brand portfolio.
  • C. Ermontoise
    Ermontoise is the French demonym referring to a female inhabitant or native of the town of Ermont in France.
  • D. Brière
    Brière is a French-language surname most prominently associated with former NHL player and current hockey executive Daniel Brière.
  • E. Ferrière
    Ferrière is a French-language surname of Swiss origin borne by various notable individuals, including social worker and humanitarian Suzanne Ferrière.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668eed2e88190b54b15e6545dbdf8 completed April 20, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a52875c28819083e888910961856b completed May 17, 2026, 11:43 p.m.
NEDg Description generation batch_6a0a53daee588190a091256cdc942bc3 completed May 17, 2026, 11:48 p.m.
NED2 Entity disambiguation (via description) batch_6a0a54570b8c819089c7811b89478239 completed May 17, 2026, 11:50 p.m.
Created at: April 11, 2026, 11:36 p.m.