Triple

T17237012
Position Surface form Disambiguated ID Type / Status
Subject Haarlem school E418388 entity
Predicate hasNotableMember P304 FINISHED
Object Jan de Bray 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: Jan de Bray | Statement: [Haarlem school, hasNotableMember, Jan de Bray]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan de Bray
Context triple: [Haarlem school, hasNotableMember, Jan de Bray]
  • A. Jan de Bray chosen
    Jan de Bray was a prominent 17th-century Dutch Golden Age painter known for his refined portraits and history paintings, particularly associated with the artistic community in Haarlem.
  • B. Balthasar van der Ast
    Balthasar van der Ast was a Dutch Golden Age painter renowned for his detailed still lifes featuring flowers, shells, and insects.
  • C. Pieter de la Court
    Pieter de la Court was a 17th-century Dutch merchant and political thinker known for his influential writings defending republican government and commercial freedom in the Dutch Republic.
  • D. Jacob van Loo
    Jacob van Loo was a 17th-century Dutch Golden Age painter renowned for his elegant portraits and mythological scenes.
  • E. Hans de Wit
    Hans de Wit is a prominent Dutch scholar in international higher education, known for his extensive research, publications, and leadership in the field of internationalization of universities.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dfbc6e88190a3dd7930fd1681ac completed April 19, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:39 a.m.