Triple

T17422058
Position Surface form Disambiguated ID Type / Status
Subject Fredensborg Palace E423640 entity
Predicate locatedIn P40 FINISHED
Object Fredensborg 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: Fredensborg | Statement: [Fredensborg Palace, locatedIn, Fredensborg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fredensborg
Context triple: [Fredensborg Palace, locatedIn, Fredensborg]
  • A. Egeskov
    Egeskov is a village on the island of Funen in Denmark best known for the nearby Renaissance water castle Egeskov Castle, one of Europe’s best-preserved moated castles.
  • B. Charlottenlund chosen
    Charlottenlund is a suburban district north of central Copenhagen, Denmark, known for its affluent residential areas, coastal location, and historic royal palace and park.
  • C. Oksbøl
    Oksbøl is a town in southwestern Jutland, Denmark, known for its military training areas and historical role as a garrison location.
  • D. Fredensborg Palace
    Fredensborg Palace is a historic Danish royal residence on the island of Zealand, renowned for its baroque architecture and role as a primary home and gathering place for the Danish royal family.
  • E. Nyborg
    Nyborg is a historic coastal town and former royal seat in central Denmark, located on the island of Funen.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44237f2cc819083ca0e7e00d828fb completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.