Triple

T16471193
Position Surface form Disambiguated ID Type / Status
Subject Calw E400063 entity
Predicate twinTown P1072 FINISHED
Object Loudun
Loudun is a historic town in western France’s Vienne department, known for its medieval architecture and its association with the 17th-century Loudun possessions and witch trials.
 E1285776 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: Loudun | Statement: [Calw, twinTown, Loudun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Loudun
Context triple: [Calw, twinTown, Loudun]
  • A. Bourges
    Bourges is a historic city in central France known for its well-preserved medieval architecture and its UNESCO-listed Gothic cathedral, Saint-Étienne.
  • B. Saint-Mard
    Saint-Mard is a French commune in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
  • 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. Mâcon
    Mâcon is a historic town in eastern France’s Burgundy region, known for its wine production and picturesque setting along the Saône River.
  • E. Niort
    Niort is a historic city in western France known as an administrative and economic center, particularly for its strong mutual insurance and financial services sector.
  • 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: Loudun
Triple: [Calw, twinTown, Loudun]
Generated description
Loudun is a historic town in western France’s Vienne department, known for its medieval architecture and its association with the 17th-century Loudun possessions and witch trials.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Loudun
Target entity description: Loudun is a historic town in western France’s Vienne department, known for its medieval architecture and its association with the 17th-century Loudun possessions and witch trials.
  • A. Bourges
    Bourges is a historic city in central France known for its well-preserved medieval architecture and its UNESCO-listed Gothic cathedral, Saint-Étienne.
  • B. Saint-Mard
    Saint-Mard is a French commune in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
  • 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. Mâcon
    Mâcon is a historic town in eastern France’s Burgundy region, known for its wine production and picturesque setting along the Saône River.
  • E. Niort
    Niort is a historic city in western France known as an administrative and economic center, particularly for its strong mutual insurance and financial services sector.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32dd0d2fc81909b68b5afb00f192f completed April 18, 2026, 7:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0242d952988190b9b3eaca8fa92431 completed May 11, 2026, 8:58 p.m.
NEDg Description generation batch_6a0246f31c8c819097685337f0f14dad completed May 11, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_6a02478d775c8190ac9d14bd260e7eca completed May 11, 2026, 9:18 p.m.
Created at: April 10, 2026, 5:11 a.m.