Triple

T14123081
Position Surface form Disambiguated ID Type / Status
Subject Royal Stables (Christiansborg Palace) E339950 entity
Predicate locatedOn P40 FINISHED
Object Slotsholmen E175961 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: Slotsholmen | Statement: [Royal Stables (Christiansborg Palace), locatedOn, Slotsholmen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Slotsholmen
Context triple: [Royal Stables (Christiansborg Palace), locatedOn, Slotsholmen]
  • A. Slotsholmen chosen
    Slotsholmen is a small island in central Copenhagen that serves as Denmark’s political and administrative center, housing key institutions such as Christiansborg Palace and several government ministries.
  • B. Blasieholmen
    Blasieholmen is a central Stockholm peninsula known for its historic buildings, cultural institutions, and waterfront views across from the Old Town.
  • C. Slotssøen
    Slotssøen is the central lake in Hillerød, Denmark, best known for framing the historic Frederiksborg Castle and its surrounding park.
  • D. Thurø
    Thurø is a small Danish island in the Baltic Sea known for its coastal scenery, beaches, and traditional maritime village atmosphere.
  • E. Helgeandsholmen
    Helgeandsholmen is a small central Stockholm islet best known as the site of the Swedish Parliament building and part of the historic city core.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de6095548881908a9e66adccca92d2 completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd2801198481909f9151ca873bfc56 completed May 8, 2026, 12:02 a.m.
Created at: April 9, 2026, 10:22 p.m.