Triple

T19374685
Position Surface form Disambiguated ID Type / Status
Subject Boursorama E484635 entity
Predicate hasBrand P1500 FINISHED
Object Boursorama Banque en ligne NE NERFINISHED

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: Boursorama Banque en ligne | Statement: [Boursorama, hasBrand, Boursorama Banque en ligne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boursorama Banque en ligne
Context triple: [Boursorama, hasBrand, Boursorama Banque en ligne]
  • A. Boursorama chosen
    Boursorama is a French online bank and financial services company known for its low-cost digital banking and brokerage offerings.
  • B. Bourse de Paris
    Bourse de Paris is the historic Parisian stock exchange, long a central hub of French and European financial trading.
  • C. Bourse de Commerce
    The Bourse de Commerce is a historic circular building in central Paris that now serves as a contemporary art museum housing the Pinault Collection.
  • D. Bombay Stock Exchange
    The Bombay Stock Exchange is one of Asia’s oldest and largest stock exchanges, serving as a major financial marketplace in India for trading equities, derivatives, and other securities.
  • E. Bourse
    Bourse is a Paris Métro station in the 2nd arrondissement, named after and serving the historic Paris stock exchange area.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61a5acc4481908fecfb57af16d037 completed April 20, 2026, 12:21 p.m.
Created at: April 10, 2026, 1:35 p.m.