Triple

T18341930
Position Surface form Disambiguated ID Type / Status
Subject Jaurès E439427 entity
Predicate hasAdjacentStationOnLine 7bis P131441 FINISHED
Object Louis Blanc NE NERFINISHED

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: Louis Blanc | Statement: [Jaurès, hasAdjacentStationOnLine 7bis, Louis Blanc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louis Blanc
Context triple: [Jaurès, hasAdjacentStationOnLine 7bis, Louis Blanc]
  • A. Louis Blanc chosen
    Louis Blanc is a Paris Métro station in the 10th arrondissement that serves as an interchange between lines 7 and 7bis.
  • B. Louis Blanc
    Louis Blanc was a French socialist politician and historian best known for advocating social workshops and workers’ rights during the 1848 Revolution.
  • C. François Chauveau
    François Chauveau was a 17th-century French engraver and illustrator renowned for his book illustrations, particularly for works of French literature and fairy tales.
  • D. Jean François Leval
    Jean François Leval was a French general of the Napoleonic Wars who led troops in several key campaigns, including in the Peninsular War.
  • E. François Sauvadet
    François Sauvadet is a French centrist politician known for his long parliamentary career and leadership roles in regional and national politics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9175fec8190af865699b4e64d8c completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e514f0b5a881908056d48bc48124b8 completed April 19, 2026, 5:46 p.m.
Created at: April 10, 2026, 10:37 a.m.