Triple

T16805787
Position Surface form Disambiguated ID Type / Status
Subject Dukenburg district E408477 entity
Predicate contains P35 FINISHED
Object Tolhuis E1235746 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: Tolhuis | Statement: [Dukenburg district, contains, Tolhuis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tolhuis
Context triple: [Dukenburg district, contains, Tolhuis]
  • A. Tolhuis chosen
    Tolhuis is a residential neighborhood in the Dukenburg district of Nijmegen in the Netherlands, known for its post-war urban planning and green surroundings.
  • B. Timmerhuis
    Timmerhuis is a mixed-use, modular glass-and-steel building in Rotterdam known for its stacked, pixelated form and sustainable design.
  • C. Trippenhuis
    Trippenhuis is a historic 17th-century canal house in Amsterdam that serves as the headquarters of the Royal Netherlands Academy of Arts and Sciences.
  • D. Houten Huys
    Houten Huys is one of the oldest surviving wooden houses in Amsterdam, located in the historic Begijnhof courtyard.
  • E. Huis Ten Bosch
    Huis Ten Bosch is a Dutch-themed amusement park in Sasebo, Japan, featuring European-style architecture, canals, seasonal flower displays, and various attractions.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2cc25dc81909443b2c83155267a completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb0dce448190b20ca3d60d9fc475 completed May 10, 2026, 5:06 p.m.
Created at: April 10, 2026, 5:22 a.m.