Triple

T17789905
Position Surface form Disambiguated ID Type / Status
Subject Gerrit van der Heyden E444129 entity
Predicate relative P37 FINISHED
Object Jan van der Heyden 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 van der Heyden | Statement: [Gerrit van der Heyden, relative, Jan van der Heyden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jan van der Heyden
Context triple: [Gerrit van der Heyden, relative, Jan van der Heyden]
  • A. Jan van der Heyden chosen
    Jan van der Heyden was a 17th-century Dutch painter and inventor renowned for his detailed cityscapes and pioneering improvements in firefighting technology and street lighting.
  • B. Pieter van der Heyden
    Pieter van der Heyden was a 16th-century Flemish engraver known for reproducing and disseminating the works of prominent artists such as Pieter Bruegel the Elder.
  • C. Gerrit van der Heyden
    Gerrit van der Heyden was a Dutch Golden Age figure known primarily as the brother of the renowned painter and inventor Jan van der Heyden.
  • D. Jan van Huchtenburg
    Jan van Huchtenburg was a Dutch Golden Age painter and engraver best known for his dynamic battle scenes and equestrian portraits.
  • E. Jan van Vliet
    Jan van Vliet was a 17th-century Dutch scholar and philologist known for his work on Germanic languages and early Dutch history.
  • 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_69d8b9ef17708190bdf7e2adbf14ddc2 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4879688908190a5428b1fa7525f62 completed April 19, 2026, 7:43 a.m.
Created at: April 10, 2026, 10:13 a.m.