Triple

T15339265
Position Surface form Disambiguated ID Type / Status
Subject Rouen metropolitan area E366746 entity
Predicate hasPart P35 FINISHED
Object Saint-Martin-du-Vivier
Saint-Martin-du-Vivier is a small commune in northern France that forms part of the suburban area surrounding the city of Rouen in Normandy.
E1151402 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: Saint-Martin-du-Vivier | Statement: [Rouen metropolitan area, hasPart, Saint-Martin-du-Vivier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint-Martin-du-Vivier
Context triple: [Rouen metropolitan area, hasPart, Saint-Martin-du-Vivier]
  • A. Saint-Martin-en-Haut
    Saint-Martin-en-Haut is a rural commune in eastern France situated in the scenic Monts du Lyonnais, known for its hilly landscapes and agricultural character.
  • B. Valtournenche
    Valtournenche is a mountain village and commune in Italy’s Aosta Valley, known as a gateway to the Matterhorn and a popular destination for alpine climbing and skiing.
  • C. Vaujours
    Vaujours is a small suburban commune in the northeastern outskirts of Paris, France.
  • D. Saint-Véran
    Saint-Véran is a French wine appellation in southern Burgundy known for its high-quality Chardonnay-based white wines.
  • E. Villaz-Saint-Pierre
    Villaz-Saint-Pierre is a small municipality in the canton of Fribourg in western Switzerland.
  • 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: Saint-Martin-du-Vivier
Triple: [Rouen metropolitan area, hasPart, Saint-Martin-du-Vivier]
Generated description
Saint-Martin-du-Vivier is a small commune in northern France that forms part of the suburban area surrounding the city of Rouen in Normandy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saint-Martin-du-Vivier
Target entity description: Saint-Martin-du-Vivier is a small commune in northern France that forms part of the suburban area surrounding the city of Rouen in Normandy.
  • A. Saint-Martin-en-Haut
    Saint-Martin-en-Haut is a rural commune in eastern France situated in the scenic Monts du Lyonnais, known for its hilly landscapes and agricultural character.
  • B. Valtournenche
    Valtournenche is a mountain village and commune in Italy’s Aosta Valley, known as a gateway to the Matterhorn and a popular destination for alpine climbing and skiing.
  • C. Vaujours
    Vaujours is a small suburban commune in the northeastern outskirts of Paris, France.
  • D. Saint-Véran
    Saint-Véran is a French wine appellation in southern Burgundy known for its high-quality Chardonnay-based white wines.
  • E. Villaz-Saint-Pierre
    Villaz-Saint-Pierre is a small municipality in the canton of Fribourg in western Switzerland.
  • 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e12eb7c8190944a260aa1aa9156 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01f2ee9c819080fce24ed13a07c7 completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02a62dcc819087eddd2f0b4c29cb completed May 9, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69ff036153588190ae46fcde257eb3cb completed May 9, 2026, 9:50 a.m.
Created at: April 10, 2026, 3:17 a.m.