Triple

T4109078
Position Surface form Disambiguated ID Type / Status
Subject Paris Métro Line 13 E88523 entity
Predicate hasStation P35 FINISHED
Object Brochant
Brochant is a Paris Métro station in the 17th arrondissement, serving the Batignolles neighborhood on the city's northwestern side.
E414198 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: Brochant | Statement: [Paris Métro Line 13, hasStation, Brochant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brochant
Context triple: [Paris Métro Line 13, hasStation, Brochant]
  • A. Hoschedé
    Hoschedé is a French surname notably associated with the family closely linked to Impressionist painter Claude Monet.
  • B. Gouvy
    Gouvy is a rural municipality in the Belgian province of Luxembourg, known for its natural landscapes and proximity to the Ardennes region.
  • C. Melissant
    Melissant is a small village in the Dutch province of South Holland, located on the island of Goeree-Overflakkee.
  • D. Bouzy
    Bouzy is a renowned Grand Cru wine-producing village in France’s Champagne region, celebrated for its high-quality Pinot Noir grapes and distinctive sparkling wines.
  • E. Batavorum
    Batavorum is a Latin toponym referring to the Batavi, an ancient Germanic tribe whose name appears in several Roman-era place names.
  • 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: Brochant
Triple: [Paris Métro Line 13, hasStation, Brochant]
Generated description
Brochant is a Paris Métro station in the 17th arrondissement, serving the Batignolles neighborhood on the city's northwestern side.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brochant
Target entity description: Brochant is a Paris Métro station in the 17th arrondissement, serving the Batignolles neighborhood on the city's northwestern side.
  • A. Hoschedé
    Hoschedé is a French surname notably associated with the family closely linked to Impressionist painter Claude Monet.
  • B. Gouvy
    Gouvy is a rural municipality in the Belgian province of Luxembourg, known for its natural landscapes and proximity to the Ardennes region.
  • C. Melissant
    Melissant is a small village in the Dutch province of South Holland, located on the island of Goeree-Overflakkee.
  • D. Bouzy
    Bouzy is a renowned Grand Cru wine-producing village in France’s Champagne region, celebrated for its high-quality Pinot Noir grapes and distinctive sparkling wines.
  • E. Batavorum
    Batavorum is a Latin toponym referring to the Batavi, an ancient Germanic tribe whose name appears in several Roman-era place names.
  • 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_69aed9484fb881909146f4c772ad277c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af01da2b88819088a45401c0ec743a completed March 9, 2026, 5:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b850d588190a0fc4b784bc7ca4f completed March 14, 2026, 2:07 p.m.
NEDg Description generation batch_69b56f7c95988190991350cfbdda9dde completed March 14, 2026, 2:23 p.m.
NED2 Entity disambiguation (via description) batch_69b56fd9293c8190ac60091bc4c447ef completed March 14, 2026, 2:25 p.m.
Created at: March 9, 2026, 3:40 p.m.