Triple

T17070567
Position Surface form Disambiguated ID Type / Status
Subject Accor Arena E414206 entity
Predicate locatedInNeighborhood P40 FINISHED
Object Bercy E828811 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: Bercy | Statement: [Accor Arena, locatedInNeighborhood, Bercy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bercy
Context triple: [Accor Arena, locatedInNeighborhood, Bercy]
  • A. 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.
  • B. Billancourt
    Billancourt is a Paris Métro station in Boulogne-Billancourt serving the western suburbs of the French capital.
  • C. Bercy station chosen
    Bercy station is a Paris Métro and railway station in the 12th arrondissement that serves the Bercy district and provides access to major venues and intercity train services.
  • D. Bercy Village
    Bercy Village is a renovated former wine warehouse district in eastern Paris that now serves as a popular open-air shopping, dining, and leisure destination.
  • E. Buré
    Buré is a small commune in the Orne department of northwestern France.
  • 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_69d886cef44c8190ba56c44b4e863e64 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dbc0982c8190916f9905ddb5e575 completed April 18, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01235278d48190bacc7881b9eb1ea1 completed May 11, 2026, 12:31 a.m.
Created at: April 10, 2026, 5:34 a.m.