Triple

T16267072
Position Surface form Disambiguated ID Type / Status
Subject Treaty of Ardres E394902 entity
Predicate signedAt P441 FINISHED
Object Ardres
Ardres is a small town in northern France near Calais, historically notable as the site of significant diplomatic meetings and treaties between England and France.
E1228533 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: Ardres | Statement: [Treaty of Ardres, signedAt, Ardres]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ardres
Context triple: [Treaty of Ardres, signedAt, Ardres]
  • A. Anthisnes
    Anthisnes is a municipality in the province of Liège in Wallonia, Belgium.
  • B. Lothier
    Lothier was a medieval duchy in the Low Countries, historically associated with the Duchy of Brabant and forming part of the Holy Roman Empire.
  • C. Auxerre
    Auxerre is a historic city in the Burgundy region of central France, known for its medieval architecture, Gothic cathedral, and role as a regional cultural and economic center.
  • D. Praz-sur-Arly
    Praz-sur-Arly is a French Alpine village and ski resort in the Haute-Savoie department, known for its mountain scenery and winter sports tourism.
  • E. L’Arbresle
    L’Arbresle is a small commune in eastern France’s Auvergne-Rhône-Alpes region, known for its historic town center and proximity to Lyon.
  • 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: Ardres
Triple: [Treaty of Ardres, signedAt, Ardres]
Generated description
Ardres is a small town in northern France near Calais, historically notable as the site of significant diplomatic meetings and treaties between England and France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ardres
Target entity description: Ardres is a small town in northern France near Calais, historically notable as the site of significant diplomatic meetings and treaties between England and France.
  • A. Anthisnes
    Anthisnes is a municipality in the province of Liège in Wallonia, Belgium.
  • B. Lothier
    Lothier was a medieval duchy in the Low Countries, historically associated with the Duchy of Brabant and forming part of the Holy Roman Empire.
  • C. Auxerre
    Auxerre is a historic city in the Burgundy region of central France, known for its medieval architecture, Gothic cathedral, and role as a regional cultural and economic center.
  • D. Praz-sur-Arly
    Praz-sur-Arly is a French Alpine village and ski resort in the Haute-Savoie department, known for its mountain scenery and winter sports tourism.
  • E. L’Arbresle
    L’Arbresle is a small commune in eastern France’s Auvergne-Rhône-Alpes region, known for its historic town center and proximity to Lyon.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c963ec8190b059fecac6248cd9 completed April 17, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a2156008190a079c9f1b721d40a completed May 10, 2026, 1:37 p.m.
NEDg Description generation batch_6a008e33240c81908b85e261bfe64ec7 completed May 10, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a008ea7f69881909f5425d2fcc15223 completed May 10, 2026, 1:56 p.m.
Created at: April 10, 2026, 5:05 a.m.