Triple

T2028062
Position Surface form Disambiguated ID Type / Status
Subject Houffalize E44453 entity
Predicate locatedNear P294 FINISHED
Object La Roche-en-Ardenne
La Roche-en-Ardenne is a picturesque town in Belgium’s Ardennes region, known for its medieval castle ruins, outdoor activities, and World War II history.
E263392 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: La Roche-en-Ardenne | Statement: [Houffalize, locatedNear, La Roche-en-Ardenne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: La Roche-en-Ardenne
Context triple: [Houffalize, locatedNear, La Roche-en-Ardenne]
  • A. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • B. Wavre
    Wavre is a town in central Belgium that serves as the capital of Walloon Brabant and is known for hosting the Walibi Belgium amusement park.
  • C. Raeren
    Raeren is a municipality in eastern Belgium known for its German-speaking population and historical stoneware pottery tradition.
  • D. Namur
    Namur is a historic Belgian city and the capital of Wallonia, located at the confluence of the Meuse and Sambre rivers.
  • E. Vandoeuvres
    Vandoeuvres is a small, affluent residential municipality located near the city of Geneva 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: La Roche-en-Ardenne
Triple: [Houffalize, locatedNear, La Roche-en-Ardenne]
Generated description
La Roche-en-Ardenne is a picturesque town in Belgium’s Ardennes region, known for its medieval castle ruins, outdoor activities, and World War II history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: La Roche-en-Ardenne
Target entity description: La Roche-en-Ardenne is a picturesque town in Belgium’s Ardennes region, known for its medieval castle ruins, outdoor activities, and World War II history.
  • A. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • B. Wavre
    Wavre is a town in central Belgium that serves as the capital of Walloon Brabant and is known for hosting the Walibi Belgium amusement park.
  • C. Raeren
    Raeren is a municipality in eastern Belgium known for its German-speaking population and historical stoneware pottery tradition.
  • D. Namur
    Namur is a historic Belgian city and the capital of Wallonia, located at the confluence of the Meuse and Sambre rivers.
  • E. Vandoeuvres
    Vandoeuvres is a small, affluent residential municipality located near the city of Geneva 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_69a889144f2481909932f0746a93023d completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb911e5dc819097e40af0da4d01e7 completed March 7, 2026, 5:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3ae5cb48190bd6d1ed21f56fe2a completed March 9, 2026, 11:49 a.m.
NEDg Description generation batch_69aeb48dfbfc81908193c909315bd030 completed March 9, 2026, 11:52 a.m.
NED2 Entity disambiguation (via description) batch_69aeb57af28c8190bfca30ad3e7ca8b3 completed March 9, 2026, 11:56 a.m.
Created at: March 4, 2026, 7:38 p.m.