Triple

T1568620
Position Surface form Disambiguated ID Type / Status
Subject Gävleborg County E33488 entity
Predicate containsTown P847 FINISHED
Object Bollnäs
Bollnäs is a small Swedish town known for its scenic lakeside setting, traditional wooden architecture, and strong bandy sports culture.
E186086 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: Bollnäs | Statement: [Gävleborg County, containsTown, Bollnäs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bollnäs
Context triple: [Gävleborg County, containsTown, Bollnäs]
  • A. Bollstanäs
    Bollstanäs is a residential locality in Sweden situated within the suburban area of Upplands Väsby, north of Stockholm.
  • B. Hovsjö
    Hovsjö is a residential district in the city of Södertälje, Sweden, known for its large-scale housing estates and diverse population.
  • C. Trollbäcken
    Trollbäcken is a residential suburban district in the Stockholm County area of Sweden, known for its proximity to lakes and green spaces.
  • D. Skarpäng
    Skarpäng is a residential urban area within Täby Municipality in Stockholm County, Sweden.
  • E. Strängnäs
    Strängnäs is a historic Swedish town known for its medieval cathedral and picturesque location on the shores of Lake Mälaren.
  • 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: Bollnäs
Triple: [Gävleborg County, containsTown, Bollnäs]
Generated description
Bollnäs is a small Swedish town known for its scenic lakeside setting, traditional wooden architecture, and strong bandy sports culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bollnäs
Target entity description: Bollnäs is a small Swedish town known for its scenic lakeside setting, traditional wooden architecture, and strong bandy sports culture.
  • A. Bollstanäs
    Bollstanäs is a residential locality in Sweden situated within the suburban area of Upplands Väsby, north of Stockholm.
  • B. Hovsjö
    Hovsjö is a residential district in the city of Södertälje, Sweden, known for its large-scale housing estates and diverse population.
  • C. Trollbäcken
    Trollbäcken is a residential suburban district in the Stockholm County area of Sweden, known for its proximity to lakes and green spaces.
  • D. Skarpäng
    Skarpäng is a residential urban area within Täby Municipality in Stockholm County, Sweden.
  • E. Strängnäs
    Strängnäs is a historic Swedish town known for its medieval cathedral and picturesque location on the shores of Lake Mälaren.
  • 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_69a885f11b048190935025a035302715 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908a15e308190b8bec55d1712812a completed March 5, 2026, 4:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad608813548190b156fb9470ed3239 completed March 8, 2026, 11:42 a.m.
NEDg Description generation batch_69ad61bdb07c8190b0bd0c2298e9d2b5 completed March 8, 2026, 11:47 a.m.
NED2 Entity disambiguation (via description) batch_69ad622acf5881908add72069bd2f060 completed March 8, 2026, 11:48 a.m.
Created at: March 4, 2026, 7:27 p.m.