Triple

T2122322
Position Surface form Disambiguated ID Type / Status
Subject Seine-et-Marne E43951 entity
Predicate subprefecture P9697 FINISHED
Object Provins
Provins is a historic medieval town in north-central France renowned for its well-preserved fortifications and UNESCO World Heritage status.
E326197 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: Provins | Statement: [Seine-et-Marne, subprefecture, Provins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Provins
Context triple: [Seine-et-Marne, subprefecture, Provins]
  • A. Tournus
    Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
  • B. Dijon
    Dijon is a historic city in eastern France renowned for its rich architectural heritage, former status as the capital of the Duchy of Burgundy, and its famous mustard.
  • C. Brioude
    Brioude is a historic town in south-central France known for its Romanesque Basilica of Saint-Julien and its location in the Haute-Loire department of the Auvergne region.
  • D. Montélimar
    Montélimar is a town in southeastern France, known as the "gateway to Provence" and famous for its traditional nougat confectionery.
  • E. Mâcon
    Mâcon is a historic town in eastern France’s Burgundy region, known for its wine production and picturesque setting along the Saône River.
  • 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: Provins
Triple: [Seine-et-Marne, subprefecture, Provins]
Generated description
Provins is a historic medieval town in north-central France renowned for its well-preserved fortifications and UNESCO World Heritage status.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Provins
Target entity description: Provins is a historic medieval town in north-central France renowned for its well-preserved fortifications and UNESCO World Heritage status.
  • A. Tournus
    Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
  • B. Dijon
    Dijon is a historic city in eastern France renowned for its rich architectural heritage, former status as the capital of the Duchy of Burgundy, and its famous mustard.
  • C. Brioude
    Brioude is a historic town in south-central France known for its Romanesque Basilica of Saint-Julien and its location in the Haute-Loire department of the Auvergne region.
  • D. Montélimar
    Montélimar is a town in southeastern France, known as the "gateway to Provence" and famous for its traditional nougat confectionery.
  • E. Mâcon
    Mâcon is a historic town in eastern France’s Burgundy region, known for its wine production and picturesque setting along the Saône River.
  • 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_69a88717cfe48190b7ecdd68c824848a completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb51e8088190a1aeafee4e8dff63 completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69b2031a55148190a1b96af35d109259 completed March 12, 2026, 12:04 a.m.
NEDg Description generation batch_69b20402ca548190846ffc5b39c66acb completed March 12, 2026, 12:08 a.m.
NED2 Entity disambiguation (via description) batch_69b2045e8cfc8190aba6b6b2d16ddd26 completed March 12, 2026, 12:10 a.m.
Created at: March 4, 2026, 7:44 p.m.