Triple

T18736130
Position Surface form Disambiguated ID Type / Status
Subject Dirck van Hoogstraten E458167 entity
Predicate relative P37 FINISHED
Object Samuel van Hoogstraten E97198 NE FINISHED

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: Samuel van Hoogstraten | Statement: [Dirck van Hoogstraten, relative, Samuel van Hoogstraten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samuel van Hoogstraten
Context triple: [Dirck van Hoogstraten, relative, Samuel van Hoogstraten]
  • A. Samuel van Hoogstraten chosen
    Samuel van Hoogstraten was a Dutch Golden Age painter, writer, and art theorist known for his trompe-l'œil works and influential treatise on painting.
  • B. Dirck van Hoogstraten
    Dirck van Hoogstraten was a Dutch Golden Age painter known for his genre scenes and as a member of a prominent family of artists.
  • C. Jan de Wit
    Jan de Wit is a Dutch computer programmer best known for creating the infamous Anna Kournikova email worm that spread rapidly across the internet in 2001.
  • D. Jacob de Wit
    Jacob de Wit was an 18th-century Dutch painter and draftsman renowned for his Rococo-style religious and mythological works, particularly his ceiling and wall decorations in Amsterdam.
  • E. Hendrik de Wit
    Hendrik de Wit is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the surname De Wit.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e57689fa508190ad821d361cba9edf completed April 20, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05829d831881908540c140791d6fb6 completed May 14, 2026, 8:06 a.m.
Created at: April 10, 2026, 11:51 a.m.