Triple

T18401564
Position Surface form Disambiguated ID Type / Status
Subject AFP E450008 entity
Predicate foundedBy P104 FINISHED
Object Charles-Louis Havas 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: Charles-Louis Havas | Statement: [AFP, foundedBy, Charles-Louis Havas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles-Louis Havas
Context triple: [AFP, foundedBy, Charles-Louis Havas]
  • A. Charles-Louis Havas chosen
    Charles-Louis Havas was a 19th-century French businessman and pioneer of modern news agencies who founded the organization that later became Agence France-Presse.
  • B. Albert-Ernest Carrier-Belleuse
    Albert-Ernest Carrier-Belleuse was a prominent 19th-century French sculptor known for his ornate, eclectic style and influential role in decorative and monumental sculpture.
  • C. Guy-Victor Duperré
    Guy-Victor Duperré was a prominent 19th-century French naval officer who rose to the highest ranks of the French Navy and played key roles in the Napoleonic Wars and French colonial campaigns.
  • D. Eugène Ferret
    Eugène Ferret was an architect best known for designing the historic Sanremo Casino in Italy.
  • E. Georges Blanchard
    Georges Blanchard was a French general best known for his leadership of French forces during the early stages of World War II, particularly in the 1940 Battle of France.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5195185b08190bd3b5471cdc047b0 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.