Triple

T17363303
Position Surface form Disambiguated ID Type / Status
Subject Palazzo Corsini E422122 entity
Predicate containsWorkBy P2011 FINISHED
Object Anthony van Dyck 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: Anthony van Dyck | Statement: [Palazzo Corsini, containsWorkBy, Anthony van Dyck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony van Dyck
Context triple: [Palazzo Corsini, containsWorkBy, Anthony van Dyck]
  • A. Anthony van Dyck chosen
    Anthony van Dyck was a Flemish Baroque painter renowned for his elegant and influential portraiture, especially as court painter to King Charles I of England.
  • B. Peter Paul Rubens
    Peter Paul Rubens was a prolific 17th-century Flemish Baroque painter renowned for his dynamic compositions, vibrant color, and dramatic depictions of religious, mythological, and historical subjects.
  • C. Jan Rubens
    Jan Rubens was a 16th-century German lawyer and the father of the Flemish Baroque painter Peter Paul Rubens.
  • D. Peter Lely
    Peter Lely was a prominent 17th-century portrait painter, best known as the leading court artist in England during the Restoration period.
  • E. Frans Hals
    Frans Hals was a prominent Dutch Golden Age painter renowned for his lively, expressive portraiture and innovative brushwork.
  • 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_69e43a4e3c3481909dfaa00334c5010e completed April 19, 2026, 2:13 a.m.
Created at: April 10, 2026, 5:44 a.m.