Triple

T17355394
Position Surface form Disambiguated ID Type / Status
Subject Noel Desenfans E421920 entity
Predicate name P16 FINISHED
Object Noel Desenfans 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: Noel Desenfans | Statement: [Noel Desenfans, name, Noel Desenfans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Noel Desenfans
Context triple: [Noel Desenfans, name, Noel Desenfans]
  • A. Noel Desenfans chosen
    Noel Desenfans was an 18th–19th century French-born art dealer and collector who became a key figure in the British art world and co-founded the Dulwich Picture Gallery.
  • B. Roger Degueldre
    Roger Degueldre was a French Army officer best known as a leading figure and commando leader in the pro–French Algeria paramilitary underground during the Algerian War.
  • C. Yvan Delporte
    Yvan Delporte was a Belgian comics writer and editor best known for his influential work on the Smurfs franchise and other Franco-Belgian comics.
  • D. Jacques Thienpont
    Jacques Thienpont is a renowned Belgian winemaker best known for creating the cult Bordeaux wine Le Pin in Pomerol.
  • E. Benoit Dageville
    Benoit Dageville is a French computer scientist and entrepreneur best known as a co-founder of the cloud data platform company Snowflake.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a487bd8819081c6d1e4aa466d6f completed April 19, 2026, 2:13 a.m.
Created at: April 10, 2026, 5:44 a.m.