Triple

T10047144
Position Surface form Disambiguated ID Type / Status
Subject Saint-Michel (Paris Métro) E207643 entity
Predicate hasEntranceNear P3449 FINISHED
Object Pont Saint-Michel E225065 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: Pont Saint-Michel | Statement: [Saint-Michel (Paris Métro), hasEntranceNear, Pont Saint-Michel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pont Saint-Michel
Context triple: [Saint-Michel (Paris Métro), hasEntranceNear, Pont Saint-Michel]
  • A. Pont Saint-Michel chosen
    Pont Saint-Michel is a historic bridge in central Paris that spans the Seine, linking the Île de la Cité to the Left Bank near notable landmarks such as Notre-Dame Cathedral.
  • B. Pont Vieux
    Pont Vieux is a historic medieval bridge in Albi, France, spanning the Tarn River and connecting the old town with the opposite bank.
  • C. Pont Vieux
    Pont Vieux is a historic medieval stone bridge in Carcassonne, France, that spans the Aude River and links the fortified cité with the lower town.
  • D. Pont Neuf
    Pont Neuf is the oldest standing bridge in Paris, renowned for its historic stone arches and its role linking the Île de la Cité with both banks of the city.
  • E. Pont Neuf
    Pont Neuf is a historic stone arch bridge spanning the Garonne River in Toulouse, France, and one of the city’s most iconic landmarks.
  • 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_69ca835ad0608190b7c80b292da004f5 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcf664dd881908786fcd802bf10da completed April 2, 2026, 2:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6528677f88190b259d5a25ddc290b completed April 8, 2026, 1:05 p.m.
Created at: March 30, 2026, 8:56 p.m.