Triple

T13852722
Position Surface form Disambiguated ID Type / Status
Subject Hôtel de Thellusson E332983 entity
Predicate streetAddress P606 FINISHED
Object Rue de Provence — NE NERFINISHED

How this triple was built (3 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: Rue de Provence | Statement: [Hôtel de Thellusson, streetAddress, Rue de Provence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rue de Provence
Context triple: [Hôtel de Thellusson, streetAddress, Rue de Provence]
  • A. Rue du Sentier
    Rue du Sentier is a historic street in central Paris long associated with the textile and garment trade, now also known for its tech startups and media companies.
  • B. Rue Vignon
    Rue Vignon is a street in central Paris located near the Place de la Madeleine, known for its elegant Haussmann-era architecture and proximity to major shopping and business districts.
  • C. Rue de Trèves
    Rue de Trèves is a central street in Brussels’ European Quarter, known for its proximity to key European Union institutions and the Place du Luxembourg.
  • D. Rue de Lisbonne
    Rue de Lisbonne is a street in Paris’s 8th arrondissement, known for its Haussmann-era architecture and proximity to the elegant Parc Monceau.
  • E. Rue de l'Abreuvoir
    Rue de l'Abreuvoir is a picturesque, winding cobblestone street in Paris’s Montmartre district, known for its historic charm, ivy-covered houses, and iconic views of the Sacré-Cœur.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rue de Provence
Target entity description: Rue de Provence is a street in Paris, France, located in the 9th arrondissement and known for its historic Haussmann-era architecture and central urban setting.
  • A. Rue du Sentier
    Rue du Sentier is a historic street in central Paris long associated with the textile and garment trade, now also known for its tech startups and media companies.
  • B. Rue Vignon
    Rue Vignon is a street in central Paris located near the Place de la Madeleine, known for its elegant Haussmann-era architecture and proximity to major shopping and business districts.
  • C. Rue de Trèves
    Rue de Trèves is a central street in Brussels’ European Quarter, known for its proximity to key European Union institutions and the Place du Luxembourg.
  • D. Rue de Lisbonne
    Rue de Lisbonne is a street in Paris’s 8th arrondissement, known for its Haussmann-era architecture and proximity to the elegant Parc Monceau.
  • E. Rue de l'Abreuvoir
    Rue de l'Abreuvoir is a picturesque, winding cobblestone street in Paris’s Montmartre district, known for its historic charm, ivy-covered houses, and iconic views of the Sacré-Cœur.
  • F. None of above. chosen

Provenance (2 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02da9460819093a3ec5a3c62ea81 completed April 14, 2026, 9:03 a.m.
Created at: April 9, 2026, 10:14 p.m.