Triple

T494357
Position Surface form Disambiguated ID Type / Status
Subject AAE E10257 entity
Predicate garrison P75 FINISHED
Object Hôtel de Brienne E18114 NE FINISHED

How this triple was built (2 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: Hôtel de Brienne | Statement: [AAE, garrison, Hôtel de Brienne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hôtel de Brienne
Context triple: [AAE, garrison, Hôtel de Brienne]
  • A. Château de Boncourt
    Château de Boncourt was a French estate best known as the birthplace of the German Romantic poet and botanist Adelbert von Chamisso.
  • B. Maison Guiette
    Maison Guiette is a modernist residential building in Antwerp, Belgium, designed by Le Corbusier and recognized as part of his UNESCO World Heritage-listed works.
  • C. Hôtel de Brienne, Paris chosen
    The Hôtel de Brienne in Paris is a historic 18th-century mansion that serves as France’s Ministry of the Armed Forces and a key military administrative headquarters.
  • D. Brienne-le-Château
    Brienne-le-Château is a commune in northeastern France best known as the town where Napoleon Bonaparte attended military school in his youth.
  • E. Hôtel de Salm
    The Hôtel de Salm is a prominent neoclassical palace in Paris that serves as the historic seat of France’s Légion d'honneur.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f0fbfa408190aeb3b93996a35c00 completed Feb. 28, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69a47d2c33bc81909d0743ca3ef96c00 completed March 1, 2026, 5:53 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.