Triple

T1051358
Position Surface form Disambiguated ID Type / Status
Subject Trocadéro E22704 entity
Predicate connectedByBridgeTo P845 FINISHED
Object Pont d’Iéna E81843 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 d’Iéna | Statement: [Trocadéro, connectedByBridgeTo, Pont d’Iéna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pont d’Iéna
Context triple: [Trocadéro, connectedByBridgeTo, Pont d’Iéna]
  • A. Pont d’Iéna chosen
    Pont d’Iéna is a 19th-century bridge in Paris that spans the Seine between the Eiffel Tower and the Trocadéro, offering iconic views of the city’s landmarks.
  • B. Pont de Mirabeau
    Pont de Mirabeau is a bridge spanning the Durance River in southeastern France, known for carrying road traffic across this major waterway.
  • C. Pont d’Ain
    Pont d’Ain is a French commune in the Ain department of eastern France, known for its historic bridge over the Ain River and its picturesque riverside setting.
  • D. Pont de Neuilly
    Pont de Neuilly is a bridge over the Seine in the western suburbs of Paris, connecting the city of Neuilly-sur-Seine to the La Défense business district.
  • E. Pont de Bir-Hakeim
    Pont de Bir-Hakeim is a two-level bridge in Paris spanning the Seine, notable for carrying both motor traffic and Line 6 of the Métro and for its frequent appearance in films and photography.
  • 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_69a493da02e081908c13ff5e02a0fe7a completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b8b5312081909796df58fa7c1e9d completed March 1, 2026, 10:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac4c1b4c3481909ec58291dc9cc32f completed March 7, 2026, 4:02 p.m.
Created at: March 1, 2026, 7:42 p.m.