Triple

T22078415
Position Surface form Disambiguated ID Type / Status
Subject Vika E545581 entity
Predicate hasStreet P959 FINISHED
Object Dokkveien
Dokkveien is a street located in the Vika neighborhood of central Oslo, Norway, near the city’s waterfront and business district.
 E1518610 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: Dokkveien | Statement: [Vika, hasStreet, Dokkveien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dokkveien
Context triple: [Vika, hasStreet, Dokkveien]
  • A. Sporveien
    Sporveien is the municipally owned public transport company in Oslo that operates key parts of the city's metro, tram, and bus infrastructure.
  • B. Kirkegata
    Kirkegata is a central street in Oslo, Norway, known for its historic buildings and proximity to major city squares and landmarks.
  • C. Svenskens vei
    Svenskens vei is a street located in the Vålerenga neighborhood of Oslo, Norway.
  • D. Munkedamsveien
    Munkedamsveien is a central street in Oslo, Norway, known for hosting major cultural venues and offices near the city’s waterfront.
  • E. Lysebotnvegen
    Lysebotnvegen is a scenic mountain road in Norway known for its dramatic hairpin bends, steep climbs, and panoramic views over the Lysefjord.
  • 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: Dokkveien
Triple: [Vika, hasStreet, Dokkveien]
Generated description
Dokkveien is a street located in the Vika neighborhood of central Oslo, Norway, near the city’s waterfront and business district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dokkveien
Target entity description: Dokkveien is a street located in the Vika neighborhood of central Oslo, Norway, near the city’s waterfront and business district.
  • A. Sporveien
    Sporveien is the municipally owned public transport company in Oslo that operates key parts of the city's metro, tram, and bus infrastructure.
  • B. Kirkegata
    Kirkegata is a central street in Oslo, Norway, known for its historic buildings and proximity to major city squares and landmarks.
  • C. Svenskens vei
    Svenskens vei is a street located in the Vålerenga neighborhood of Oslo, Norway.
  • D. Munkedamsveien
    Munkedamsveien is a central street in Oslo, Norway, known for hosting major cultural venues and offices near the city’s waterfront.
  • E. Lysebotnvegen
    Lysebotnvegen is a scenic mountain road in Norway known for its dramatic hairpin bends, steep climbs, and panoramic views over the Lysefjord.
  • 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_69e11e3523488190badd54b5d580c00d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b43df0819090c248ded98fad12 completed April 28, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a8793a1ec8190977047d2c094845d completed May 18, 2026, 3:29 a.m.
NEDg Description generation batch_6a0a8a706f8481908e3c09c936948576 completed May 18, 2026, 3:41 a.m.
NED2 Entity disambiguation (via description) batch_6a0a8aeed53c8190a261573a43a03929 completed May 18, 2026, 3:43 a.m.
Created at: April 16, 2026, 8:28 p.m.