Triple

T16034302
Position Surface form Disambiguated ID Type / Status
Subject Theo van de Sande E388927 entity
Predicate familyName P18 FINISHED
Object van de Sande E388927 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: van de Sande | Statement: [Theo van de Sande, familyName, van de Sande]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: van de Sande
Context triple: [Theo van de Sande, familyName, van de Sande]
  • A. Theo van de Sande chosen
    Theo van de Sande is a Dutch cinematographer known for his work on both European films and Hollywood comedies, including collaborations with director Dennis Dugan.
  • B. van Heutsz
    Van Heutsz is a Dutch surname most prominently associated with Johannes Benedictus van Heutsz, a colonial military leader and Governor-General of the Dutch East Indies.
  • C. van Slingelandt
    Van Slingelandt is a Dutch surname historically associated with a prominent political and administrative family in the Netherlands.
  • D. van de Velde
    Van de Velde is a Dutch surname borne by several notable figures, including artists, designers, and writers from the Low Countries.
  • E. van Swanenburg
    Van Swanenburg is a Dutch family name historically associated with artists and notable figures from the Netherlands.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833a5aa88190a5cc3f82d55f5b62 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe474f89c819086db832b793c15ed completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:56 a.m.