Triple

T19804233
Position Surface form Disambiguated ID Type / Status
Subject Cornelis van der Geest E475767 entity
Predicate patronOf P2320 FINISHED
Object Frans Snyders 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: Frans Snyders | Statement: [Cornelis van der Geest, patronOf, Frans Snyders]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frans Snyders
Context triple: [Cornelis van der Geest, patronOf, Frans Snyders]
  • A. Frans Snyders chosen
    Frans Snyders was a prominent Flemish Baroque painter renowned for his dynamic still lifes, animal scenes, and hunting compositions, often collaborating with leading artists of his time.
  • B. Pieter Snyers
    Pieter Snyers was a Flemish Baroque painter known for his still lifes and genre scenes in 17th-century Antwerp.
  • C. Godfried Maes
    Godfried Maes was a Flemish Baroque painter and draughtsman known for his religious and mythological scenes, active in Antwerp in the late 17th century.
  • D. Jan Snyders
    Jan Snyders is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the surname Snyders.
  • E. Theo Francken
    Theo Francken is a Belgian politician known for his hardline stance on immigration and prominent role within the New Flemish Alliance (N-VA).
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e654266e18819085698aed8b0e2ba8 completed April 20, 2026, 4:28 p.m.
Created at: April 10, 2026, 1:49 p.m.