Triple

T22459182
Position Surface form Disambiguated ID Type / Status
Subject A.F.Th. van der Heijden E555186 entity
Predicate pseudonym P39 FINISHED
Object Tonio van der Heijden
Tonio van der Heijden is a pseudonym used by the prominent Dutch novelist A.F.Th. van der Heijden.
E1548893 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: Tonio van der Heijden | Statement: [A.F.Th. van der Heijden, pseudonym, Tonio van der Heijden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tonio van der Heijden
Context triple: [A.F.Th. van der Heijden, pseudonym, Tonio van der Heijden]
  • A. Piet van der Heijden
    Piet van der Heijden was a key early visionary behind Efteling, helping shape the Dutch theme park’s development and identity.
  • B. Michiel Riedijk
    Michiel Riedijk is a Dutch architect, co-founder of the Rotterdam-based firm Neutelings Riedijk Architects, known for his expressive public and cultural buildings.
  • C. Bas van der Vlies
    Bas van der Vlies was a Dutch politician and long-serving parliamentary leader known for representing the orthodox Protestant principles of the Reformed Political Party (SGP).
  • D. Frank van der Meijden
    Frank van der Meijden is a Dutch local politician who serves as the mayor of the municipality of Laarbeek in the Netherlands.
  • E. Johan Hoogewijs
    Johan Hoogewijs is a Belgian composer best known for his film and television scores.
  • 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: Tonio van der Heijden
Triple: [A.F.Th. van der Heijden, pseudonym, Tonio van der Heijden]
Generated description
Tonio van der Heijden is a pseudonym used by the prominent Dutch novelist A.F.Th. van der Heijden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tonio van der Heijden
Target entity description: Tonio van der Heijden is a pseudonym used by the prominent Dutch novelist A.F.Th. van der Heijden.
  • A. Piet van der Heijden
    Piet van der Heijden was a key early visionary behind Efteling, helping shape the Dutch theme park’s development and identity.
  • B. Michiel Riedijk
    Michiel Riedijk is a Dutch architect, co-founder of the Rotterdam-based firm Neutelings Riedijk Architects, known for his expressive public and cultural buildings.
  • C. Bas van der Vlies
    Bas van der Vlies was a Dutch politician and long-serving parliamentary leader known for representing the orthodox Protestant principles of the Reformed Political Party (SGP).
  • D. Frank van der Meijden
    Frank van der Meijden is a Dutch local politician who serves as the mayor of the municipality of Laarbeek in the Netherlands.
  • E. Johan Hoogewijs
    Johan Hoogewijs is a Belgian composer best known for his film and television scores.
  • 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b7e01fc8190825c3dc024484440 completed April 29, 2026, 1:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73d2d3b08190bc85181135ddc5db completed May 18, 2026, 8:17 p.m.
NEDg Description generation batch_6a0b75ee79988190bbe911f6129f682b completed May 18, 2026, 8:26 p.m.
NED2 Entity disambiguation (via description) batch_6a0b76656b1481909ff823a310c95fda completed May 18, 2026, 8:28 p.m.
Created at: April 16, 2026, 8:48 p.m.