Triple

T6069668
Position Surface form Disambiguated ID Type / Status
Subject Midtbyen, Trondheim E135247 entity
Predicate contains P35 FINISHED
Object Stiftsgården
Stiftsgården is a large 18th-century wooden royal residence and one of the most prominent historic buildings in central Trondheim, Norway.
 E567377 NE FINISHED

How this triple was built (4 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: Stiftsgården | Statement: [Midtbyen, Trondheim, contains, Stiftsgården]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Stiftsgården
Context triple: [Midtbyen, Trondheim, contains, Stiftsgården]
  • A. Humlegården
    Humlegården is a large historic park in central Stockholm known for its green spaces, walking paths, and recreational areas.
  • B. Birka and Hovgården
    Birka and Hovgården is a UNESCO World Heritage archaeological area in Sweden that preserves one of the most important Viking Age trading centers and its associated royal estate.
  • C. Gråsten Palace
    Gråsten Palace is a Danish royal summer residence in Southern Jutland, best known as the traditional holiday retreat of the Danish monarch.
  • D. Millesgården
    Millesgården is a sculpture park and former home and studio of Swedish sculptor Carl Milles, located on the island of Lidingö near Stockholm.
  • E. Grubbegata
    Grubbegata is a street in central Oslo, Norway, known for running through the area that houses key government buildings and institutions.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Stiftsgården
Triple: [Midtbyen, Trondheim, contains, Stiftsgården]
Generated description
Stiftsgården is a large 18th-century wooden royal residence and one of the most prominent historic buildings in central Trondheim, Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Stiftsgården
Target entity description: Stiftsgården is a large 18th-century wooden royal residence and one of the most prominent historic buildings in central Trondheim, Norway.
  • A. Humlegården
    Humlegården is a large historic park in central Stockholm known for its green spaces, walking paths, and recreational areas.
  • B. Birka and Hovgården
    Birka and Hovgården is a UNESCO World Heritage archaeological area in Sweden that preserves one of the most important Viking Age trading centers and its associated royal estate.
  • C. Gråsten Palace
    Gråsten Palace is a Danish royal summer residence in Southern Jutland, best known as the traditional holiday retreat of the Danish monarch.
  • D. Millesgården
    Millesgården is a sculpture park and former home and studio of Swedish sculptor Carl Milles, located on the island of Lidingö near Stockholm.
  • E. Grubbegata
    Grubbegata is a street in central Oslo, Norway, known for running through the area that houses key government buildings and institutions.
  • F. None of above. chosen

Provenance (5 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_69c00879e8048190b690717d19c5bc03 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0574157848190bb8e0972eb55a363 completed March 22, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d349f288190833384eb9e6c7f52 completed March 23, 2026, 11 a.m.
NEDg Description generation batch_69c11ec11864819084c31d98133ca53a completed March 23, 2026, 11:06 a.m.
NED2 Entity disambiguation (via description) batch_69c11f29842881909acf88a1fa896354 completed March 23, 2026, 11:08 a.m.
Created at: March 22, 2026, 4:10 p.m.