Triple

T15922773
Position Surface form Disambiguated ID Type / Status
Subject Seine river banks E386132 entity
Predicate contains P35 FINISHED
Object Conciergerie E119509 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: Conciergerie | Statement: [Seine river banks, contains, Conciergerie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Conciergerie
Context triple: [Seine river banks, contains, Conciergerie]
  • A. Conciergerie chosen
    The Conciergerie is a former royal palace and notorious Parisian prison on the Île de la Cité, best known for holding many prisoners during the French Revolution, including Marie Antoinette.
  • B. Porte de Versailles
    Porte de Versailles is a neighborhood in southwestern Paris known for hosting the city’s largest exhibition and convention center.
  • C. Jacquemart Tower
    Jacquemart Tower is a historic clock and bell tower in Romans-sur-Isère, France, known as a prominent medieval landmark of the town.
  • D. Place des Jacobins
    Place des Jacobins is a central historic square in Lyon, France, known for its elegant 19th-century fountain and surrounding Haussmann-style architecture.
  • E. Palais du Luxembourg
    The Palais du Luxembourg is a historic Parisian palace that has served as a seat of French political power and now houses the French Senate.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156832a248190bed479bf835a469c completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5aba70c8190a74c45bce6f9b782 completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:52 a.m.