Triple

T23508512
Position Surface form Disambiguated ID Type / Status
Subject Kees van Kooten E572350 entity
Predicate hasChild P369 FINISHED
Object Kim van Kooten 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: Kim van Kooten | Statement: [Kees van Kooten, hasChild, Kim van Kooten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kim van Kooten
Context triple: [Kees van Kooten, hasChild, Kim van Kooten]
  • A. Kim van Kooten chosen
    Kim van Kooten is a Dutch actress and screenwriter known for her prominent roles in film and television and for her acclaimed work on character-driven screenplays.
  • B. Bete Denagel
    Bete Denagel is one of the rock-hewn monolithic churches in the historic Ethiopian town of Lalibela, renowned for its medieval Christian architecture and religious significance.
  • C. Jan Kleyna
    Jan Kleyna is an astronomer known for discovering small outer moons of Jupiter and contributing to the study of planetary satellites.
  • D. Kat Kerkhofs
    Kat Kerkhofs is a Belgian television presenter and media personality, known both for her own entertainment work and as the wife of professional footballer Dries Mertens.
  • E. Femke Wolting
    Femke Wolting is a Dutch film and television producer known for innovative, often internationally oriented documentaries and feature films.
  • 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_69e245b5e4208190bac8a6509867e394 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a902c0788190840d7df1b5450b4d completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:07 p.m.