Triple

T22887506
Position Surface form Disambiguated ID Type / Status
Subject Wim van de Donk E567642 entity
Predicate familyName P18 FINISHED
Object Van de Donk
Van de Donk is a Dutch surname borne by several notable figures, including politicians and professional footballers.
 E1560735 NE FINISHED

How this triple was built (4 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 Donk | Statement: [Wim van de Donk, familyName, Van de Donk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Van de Donk
Context triple: [Wim van de Donk, familyName, Van de Donk]
  • A. Rik de Jong
    Rik de Jong is a fictional character from the long-running Dutch soap opera "Goede tijden, slechte tijden," known for his dramatic storylines and complex relationships.
  • B. Sander van Doorn
    Sander van Doorn is a Dutch DJ and electronic music producer known for his influential work in trance and progressive house.
  • C. Marc de Jonge
    Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
  • D. Randy van der Elsen
    Randy van der Elsen is a musician best known as a member of the Dutch hard rock band Vandenberg.
  • E. Guus Beumer
    Guus Beumer is a Dutch curator, writer, and cultural director known for his influential work in contemporary design, fashion, and architecture.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Van de Donk
Triple: [Wim van de Donk, familyName, Van de Donk]
Generated description
Van de Donk is a Dutch surname borne by several notable figures, including politicians and professional footballers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Van de Donk
Target entity description: Van de Donk is a Dutch surname borne by several notable figures, including politicians and professional footballers.
  • A. Rik de Jong
    Rik de Jong is a fictional character from the long-running Dutch soap opera "Goede tijden, slechte tijden," known for his dramatic storylines and complex relationships.
  • B. Sander van Doorn
    Sander van Doorn is a Dutch DJ and electronic music producer known for his influential work in trance and progressive house.
  • C. Marc de Jonge
    Marc de Jonge was a French actor best known internationally for playing the Soviet Colonel Zaysen in the action film "Rambo III."
  • D. Randy van der Elsen
    Randy van der Elsen is a musician best known as a member of the Dutch hard rock band Vandenberg.
  • E. Guus Beumer
    Guus Beumer is a Dutch curator, writer, and cultural director known for his influential work in contemporary design, fashion, and architecture.
  • F. None of above. chosen

Provenance (5 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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17fc2adb4819081bce7e6849ba31a completed April 29, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bb9be4c688190820b484bea11696b completed May 19, 2026, 1:15 a.m.
NEDg Description generation batch_6a0bbb38da508190bc1d9bc8538cdbe2 completed May 19, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_6a0bbc2a2244819090ead891e1a866ed completed May 19, 2026, 1:26 a.m.
Created at: April 17, 2026, 3:40 p.m.