Triple

T19403601
Position Surface form Disambiguated ID Type / Status
Subject Tønsberg Fortress E485391 entity
Predicate locatedOn P40 FINISHED
Object Slottsfjellet hill 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: Slottsfjellet hill | Statement: [Tønsberg Fortress, locatedOn, Slottsfjellet hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Slottsfjellet hill
Context triple: [Tønsberg Fortress, locatedOn, Slottsfjellet hill]
  • A. Slottsfjellet chosen
    Slottsfjellet is a historic hill and former fortress site in Tønsberg, Norway, known for its medieval castle ruins and prominent tower overlooking the city.
  • B. Høgefjellet
    Høgefjellet is a mountain located on the island of Vågsøy in Vestland county, western Norway.
  • C. Hemnesberget
    Hemnesberget is a small coastal village in Nordland county, Norway, known for its scenic fjord-side location and role as an administrative and service center for the surrounding area.
  • D. Slettefjell
    Slettefjell is a mountain in Norway known for its scenic highland landscapes and popular hiking and skiing routes.
  • E. Kolåstinden
    Kolåstinden is a prominent alpine peak in Norway’s Sunnmøre Alps, renowned among hikers and ski mountaineers for its steep slopes and panoramic fjord views.
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6257937d081909dbc5804d2505938 completed April 20, 2026, 1:09 p.m.
Created at: April 10, 2026, 1:36 p.m.