Triple

T5270865
Position Surface form Disambiguated ID Type / Status
Subject Kolding E119252 entity
Predicate heritageSite P4220 FINISHED
Object Koldinghus Castle E506592 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: Koldinghus Castle | Statement: [Kolding, heritageSite, Koldinghus Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Koldinghus Castle
Context triple: [Kolding, heritageSite, Koldinghus Castle]
  • A. Antvorskov Castle
    Antvorskov Castle was a significant royal residence and former monastic estate on Zealand in Denmark, historically associated with Danish kings including Frederick II.
  • B. Koldinghus chosen
    Koldinghus is a historic royal castle and museum in the Danish city of Kolding, known for its dramatic ruin-restoration architecture and cultural exhibitions.
  • C. Egeskov Castle
    Egeskov Castle is a well-preserved Renaissance water castle in Denmark renowned for its historic architecture, gardens, and museum collections.
  • D. Gottorf Castle
    Gottorf Castle is a historic ducal residence in Schleswig, Germany, renowned as the former seat of the Dukes of Holstein-Gottorp and now a major cultural and museum complex.
  • E. Teleborg Castle
    Teleborg Castle is a picturesque late 19th-century romantic-style castle in Växjö, Sweden, now used for events, conferences, and as a popular tourist attraction.
  • 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_69bd446c38e081908cdaf113bdf86790 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7bff37cc819095423cf914086c1b completed March 20, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf06cb5f788190b9ee79ca15da9d58 completed March 21, 2026, 8:59 p.m.
Created at: March 20, 2026, 1:51 p.m.