Triple

T9353204
Position Surface form Disambiguated ID Type / Status
Subject Quai aux Fleurs E225067 entity
Predicate connectsTo P845 FINISHED
Object Quai de la Corse E251186 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: Quai de la Corse | Statement: [Quai aux Fleurs, connectsTo, Quai de la Corse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Quai de la Corse
Context triple: [Quai aux Fleurs, connectsTo, Quai de la Corse]
  • A. Quai de la Corse chosen
    Quai de la Corse is a riverside quay on Paris’s Île de la Cité, lining the Seine near landmarks such as the flower market and Notre-Dame Cathedral.
  • B. Quai de Bourbon
    Quai de Bourbon is a historic riverside quay on the Île Saint-Louis in central Paris, known for its elegant 17th-century townhouses and views over the Seine.
  • C. Quai de la Douane
    Quai de la Douane is a waterfront quay in the Port of Nice, France, serving as a docking and loading area for maritime traffic.
  • D. Quai de la Rapée
    Quai de la Rapée is a Paris Métro station located near the Seine in the 12th arrondissement, serving as a stop on the city’s rapid transit network.
  • E. Quai de Conti
    Quai de Conti is a historic riverside quay on the Left Bank of the Seine in central Paris, known for its cultural institutions and picturesque views.
  • 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_69ca842abfd48190949d71c3b86eeba8 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4f9515008190b01fbb43d673de2a completed April 1, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c3f6f54c8190b0320d9cb1ae356c completed April 5, 2026, 2:07 a.m.
Created at: March 30, 2026, 7:41 p.m.