Triple

T11057712
Position Surface form Disambiguated ID Type / Status
Subject Lutry E261420 entity
Predicate hasNeighboringMunicipality P224 FINISHED
Object Savigny
Savigny is a municipality in the canton of Vaud in western Switzerland, located in the district of Lavaux-Oron above Lake Geneva.
 E902746 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: Savigny | Statement: [Lutry, hasNeighboringMunicipality, Savigny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Savigny
Context triple: [Lutry, hasNeighboringMunicipality, Savigny]
  • A. Fallières
    Fallières is a French surname most notably borne by Armand Fallières, who served as President of France in the early 20th century.
  • B. Willanzheim
    Willanzheim is a small municipality in the Kitzingen district of Bavaria, Germany, known for its rural character and Franconian wine-growing tradition.
  • C. Tournus
    Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
  • D. Beuvron
    Beuvron is a small river in central France that serves as a tributary of the Loire.
  • E. Seneffe
    Seneffe is a municipality in the province of Hainaut in Wallonia, Belgium, historically notable as the site of a major 17th-century battle during the Franco-Dutch War.
  • 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: Savigny
Triple: [Lutry, hasNeighboringMunicipality, Savigny]
Generated description
Savigny is a municipality in the canton of Vaud in western Switzerland, located in the district of Lavaux-Oron above Lake Geneva.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Savigny
Target entity description: Savigny is a municipality in the canton of Vaud in western Switzerland, located in the district of Lavaux-Oron above Lake Geneva.
  • A. Fallières
    Fallières is a French surname most notably borne by Armand Fallières, who served as President of France in the early 20th century.
  • B. Willanzheim
    Willanzheim is a small municipality in the Kitzingen district of Bavaria, Germany, known for its rural character and Franconian wine-growing tradition.
  • C. Tournus
    Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
  • D. Beuvron
    Beuvron is a small river in central France that serves as a tributary of the Loire.
  • E. Seneffe
    Seneffe is a municipality in the province of Hainaut in Wallonia, Belgium, historically notable as the site of a major 17th-century battle during the Franco-Dutch War.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d798a2efa48190b290f43dfe836501 completed April 9, 2026, 12:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c86e0e6481908f091497313132c1 completed April 18, 2026, 6:07 p.m.
NEDg Description generation batch_69e3cefc00148190a1850dc6e31523c3 completed April 18, 2026, 6:35 p.m.
NED2 Entity disambiguation (via description) batch_69e3d014a644819092c76aa02b573ca9 completed April 18, 2026, 6:40 p.m.
Created at: April 8, 2026, 9:26 p.m.