Triple

T4990549
Position Surface form Disambiguated ID Type / Status
Subject Tønsberg E112118 entity
Predicate hasLandmark P105 FINISHED
Object Slottsfjellet
Slottsfjellet is a historic hill and former fortress site in Tønsberg, Norway, known for its medieval castle ruins and prominent tower overlooking the city.
 E485392 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: Slottsfjellet | Statement: [Tønsberg, hasLandmark, Slottsfjellet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Slottsfjellet
Context triple: [Tønsberg, hasLandmark, Slottsfjellet]
  • A. Kvitfjell
    Kvitfjell is a Norwegian alpine ski resort renowned for hosting major international competitions, including Olympic and World Cup events.
  • B. 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.
  • C. Hodnefjell
    Hodnefjell is an island that forms part of the Finnøy archipelago in Norway.
  • D. Hafjell
    Hafjell is a major Norwegian ski resort in the Øyer municipality, known for hosting alpine events during the 1994 Lillehammer Winter Olympics and offering extensive slopes and winter sports facilities.
  • E. Skogsvåg
    Skogsvåg is a small coastal village in western Norway, located on the island of Sotra in Vestland county.
  • 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: Slottsfjellet
Triple: [Tønsberg, hasLandmark, Slottsfjellet]
Generated description
Slottsfjellet is a historic hill and former fortress site in Tønsberg, Norway, known for its medieval castle ruins and prominent tower overlooking the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Slottsfjellet
Target entity description: Slottsfjellet is a historic hill and former fortress site in Tønsberg, Norway, known for its medieval castle ruins and prominent tower overlooking the city.
  • A. Kvitfjell
    Kvitfjell is a Norwegian alpine ski resort renowned for hosting major international competitions, including Olympic and World Cup events.
  • B. 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.
  • C. Hodnefjell
    Hodnefjell is an island that forms part of the Finnøy archipelago in Norway.
  • D. Hafjell
    Hafjell is a major Norwegian ski resort in the Øyer municipality, known for hosting alpine events during the 1994 Lillehammer Winter Olympics and offering extensive slopes and winter sports facilities.
  • E. Skogsvåg
    Skogsvåg is a small coastal village in western Norway, located on the island of Sotra in Vestland county.
  • 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_69bd441be7bc8190b530362d427b97d2 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd728141d48190a0713e6d33c50fb6 completed March 20, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a282dd08190a29b92e8e825a3bb completed March 21, 2026, 12:08 p.m.
NEDg Description generation batch_69be8d747c40819098ac5d475d60ab46 completed March 21, 2026, 12:22 p.m.
NED2 Entity disambiguation (via description) batch_69be8df7ab9c8190b1af6e32f0f33b30 completed March 21, 2026, 12:24 p.m.
Created at: March 20, 2026, 1:34 p.m.