Triple

T20631043
Position Surface form Disambiguated ID Type / Status
Subject Apeldoorn E506954 entity
Predicate hasLandmark P105 FINISHED
Object Het Loo Palace 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: Het Loo Palace | Statement: [Apeldoorn, hasLandmark, Het Loo Palace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Het Loo Palace
Context triple: [Apeldoorn, hasLandmark, Het Loo Palace]
  • A. Het Loo Palace chosen
    Het Loo Palace is a former royal palace in Apeldoorn, the Netherlands, renowned for its Baroque architecture and formal gardens and now serving as a national museum.
  • B. Het Loo
    Het Loo is a small hamlet in the municipality of Losser in the eastern Netherlands.
  • C. Kew Palace
    Kew Palace is a historic royal residence in Kew Gardens, London, best known as a retreat for King George III and his family.
  • D. Loches royal lodgings
    Loches royal lodgings is a historic former royal residence within the medieval fortified town of Loches in central France, noted for its well-preserved architecture and association with French kings.
  • E. Hampton Court
    Hampton Court is a small settlement located within the Parish of St. Thomas in the East in eastern Jamaica.
  • 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_69e0b4bd4a0081908d4e97a590a33fb2 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6ad0b0508819093c62a4ceaf860ce completed April 20, 2026, 10:47 p.m.
Created at: April 16, 2026, 11:42 a.m.