Triple

T2381509
Position Surface form Disambiguated ID Type / Status
Subject Paris Métro Line 14 E46320 entity
Predicate hasStation P35 FINISHED
Object Bercy
Bercy is a Paris Métro station serving the Bercy district, known for its proximity to the Accor Arena and the Ministry of the Economy and Finance.
E261662 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: Bercy | Statement: [Paris Métro Line 14, hasStation, Bercy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bercy
Context triple: [Paris Métro Line 14, hasStation, Bercy]
  • A. Saverne
    Saverne is a historic town in northeastern France, known for its canal, rose gardens, and the Château des Rohan.
  • B. Ermenonville
    Ermenonville is a village in northern France known for its picturesque landscape garden and as the place where philosopher Jean-Jacques Rousseau spent his final days.
  • C. Sauvy
    Sauvy is a French surname most notably borne by Alfred Sauvy, a prominent demographer, sociologist, and economist.
  • D. Bois de Vincennes
    Bois de Vincennes is a large public park on the eastern edge of Paris, France, known for its woodlands, lakes, recreational facilities, and historical role as a former royal hunting ground.
  • E. Champ-du-Moulin
    Champ-du-Moulin is a small hamlet in the Areuse gorge in the canton of Neuchâtel, Switzerland, known for its scenic river landscape and hiking trails.
  • 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: Bercy
Triple: [Paris Métro Line 14, hasStation, Bercy]
Generated description
Bercy is a Paris Métro station serving the Bercy district, known for its proximity to the Accor Arena and the Ministry of the Economy and Finance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bercy
Target entity description: Bercy is a Paris Métro station serving the Bercy district, known for its proximity to the Accor Arena and the Ministry of the Economy and Finance.
  • A. Saverne
    Saverne is a historic town in northeastern France, known for its canal, rose gardens, and the Château des Rohan.
  • B. Ermenonville
    Ermenonville is a village in northern France known for its picturesque landscape garden and as the place where philosopher Jean-Jacques Rousseau spent his final days.
  • C. Sauvy
    Sauvy is a French surname most notably borne by Alfred Sauvy, a prominent demographer, sociologist, and economist.
  • D. Bois de Vincennes
    Bois de Vincennes is a large public park on the eastern edge of Paris, France, known for its woodlands, lakes, recreational facilities, and historical role as a former royal hunting ground.
  • E. Champ-du-Moulin
    Champ-du-Moulin is a small hamlet in the Areuse gorge in the canton of Neuchâtel, Switzerland, known for its scenic river landscape and hiking trails.
  • 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_69a88a1554a48190a0180682bcf099be completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abc7b98c988190abdb4fe51bf65bde completed March 7, 2026, 6:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea8b4f85c81909e5a4eda271b73ca completed March 9, 2026, 11:02 a.m.
NEDg Description generation batch_69aeac747e488190aea9b1831ea748a8 completed March 9, 2026, 11:18 a.m.
NED2 Entity disambiguation (via description) batch_69aeadb6008481909bf1e5d1210a58b8 completed March 9, 2026, 11:23 a.m.
Created at: March 4, 2026, 7:57 p.m.