Triple

T21836530
Position Surface form Disambiguated ID Type / Status
Subject Victor Louis E539134 entity
Predicate name P16 FINISHED
Object Victor Louis 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: Victor Louis | Statement: [Victor Louis, name, Victor Louis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Victor Louis
Context triple: [Victor Louis, name, Victor Louis]
  • A. Victor Louis chosen
    Victor Louis was an 18th-century French architect renowned for his neoclassical designs, including major works in Paris and Bordeaux.
  • B. Victor Guillaume
    Victor Guillaume was a French artist associated with the École de Nancy, a movement known for its contributions to Art Nouveau in decorative arts and design.
  • C. Baudouin
    Baudouin is a French-origin surname and given name, historically associated with noble and notable families in Francophone regions.
  • D. Charles-Ernest
    Charles-Ernest is the given name of Charles-Ernest van Loo, an 18th-century French painter from the notable Van Loo family of artists.
  • E. Charles Eugène
    Charles Eugène was an 18th-century French nobleman and military leader who served as a marshal of France and naval minister during the reign of Louis XVI.
  • 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_69e0c475cda88190987d08f23caebdc1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0a7a7c368819094e0c4548be30798 completed April 28, 2026, 12:27 p.m.
Created at: April 16, 2026, 6:55 p.m.