Triple

T3722499
Position Surface form Disambiguated ID Type / Status
Subject Saint-André-lez-Lille E81668 entity
Predicate river P165 FINISHED
Object Deûle
The Deûle is a canalised river in northern France that flows through the Lille metropolitan area and serves as an important waterway for the region.
 E382455 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: Deûle | Statement: [Saint-André-lez-Lille, river, Deûle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Deûle
Context triple: [Saint-André-lez-Lille, river, Deûle]
  • A. Thieux
    Thieux is a small French commune located in the Seine-et-Marne department in the Île-de-France region in north-central France.
  • B. Valleiry
    Valleiry is a small French commune in the Haute-Savoie department of the Auvergne-Rhône-Alpes region in southeastern France, near the Swiss border.
  • C. Aue
    Aue is a town in the Ore Mountains region of Saxony, Germany, known historically for its mining industry and role as a local transport hub.
  • D. Thérain
    Thérain is a river in northern France that flows through the Oise department before joining the Oise River.
  • E. Vaudesir
    Vaudésir is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, renowned for producing some of its most refined and age-worthy Chardonnay wines.
  • 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: Deûle
Triple: [Saint-André-lez-Lille, river, Deûle]
Generated description
The Deûle is a canalised river in northern France that flows through the Lille metropolitan area and serves as an important waterway for the region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Deûle
Target entity description: The Deûle is a canalised river in northern France that flows through the Lille metropolitan area and serves as an important waterway for the region.
  • A. Thieux
    Thieux is a small French commune located in the Seine-et-Marne department in the Île-de-France region in north-central France.
  • B. Valleiry
    Valleiry is a small French commune in the Haute-Savoie department of the Auvergne-Rhône-Alpes region in southeastern France, near the Swiss border.
  • C. Aue
    Aue is a town in the Ore Mountains region of Saxony, Germany, known historically for its mining industry and role as a local transport hub.
  • D. Thérain
    Thérain is a river in northern France that flows through the Oise department before joining the Oise River.
  • E. Vaudesir
    Vaudésir is one of the prestigious Grand Cru vineyard sites in the Chablis wine region of Burgundy, renowned for producing some of its most refined and age-worthy Chardonnay wines.
  • 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_69ad8b1b7ef081908d2d381bbf54985a completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adca9ea1688190b3b8414d77960e8f completed March 8, 2026, 7:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4ce1b25088190958c427c932641e1 completed March 14, 2026, 2:55 a.m.
NEDg Description generation batch_69b4cee2a2d88190b3a82610b6ab3488 completed March 14, 2026, 2:58 a.m.
NED2 Entity disambiguation (via description) batch_69b4cf3be5988190a049d8896e94b2b0 completed March 14, 2026, 3 a.m.
Created at: March 8, 2026, 3:34 p.m.