Triple

T9700970
Position Surface form Disambiguated ID Type / Status
Subject Porvoonjoki E234773 entity
Predicate hasNameInLanguage P15 FINISHED
Object Borgå å (Swedish)
Borgå å is the Swedish name for the Porvoonjoki river in southern Finland, which flows through the city of Porvoo into the Gulf of Finland.
E814359 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: Borgå å (Swedish) | Statement: [Porvoonjoki, hasNameInLanguage, Borgå å (Swedish)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Borgå å (Swedish)
Context triple: [Porvoonjoki, hasNameInLanguage, Borgå å (Swedish)]
  • A. Borgå
    Borgå is a historic coastal city in southern Finland, known in Finnish as Porvoo and noted for its well-preserved wooden old town and medieval cathedral.
  • B. Skogås
    Skogås is a suburban district in the southern Stockholm area of Sweden, known primarily as a residential community with good commuter connections to central Stockholm.
  • C. Bogleråsen
    Bogleråsen is a residential neighborhood located in the Østensjø borough of Oslo, Norway.
  • D. Ågotnes
    Ågotnes is a village and industrial hub on the island of Sotra in Vestland county, Norway.
  • E. Vågå
    Vågå is a rural municipality in Innlandet county, Norway, known for its traditional farming landscape, historic stave church, and proximity to the Jotunheimen mountain area.
  • 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: Borgå å (Swedish)
Triple: [Porvoonjoki, hasNameInLanguage, Borgå å (Swedish)]
Generated description
Borgå å is the Swedish name for the Porvoonjoki river in southern Finland, which flows through the city of Porvoo into the Gulf of Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Borgå å (Swedish)
Target entity description: Borgå å is the Swedish name for the Porvoonjoki river in southern Finland, which flows through the city of Porvoo into the Gulf of Finland.
  • A. Borgå
    Borgå is a historic coastal city in southern Finland, known in Finnish as Porvoo and noted for its well-preserved wooden old town and medieval cathedral.
  • B. Skogås
    Skogås is a suburban district in the southern Stockholm area of Sweden, known primarily as a residential community with good commuter connections to central Stockholm.
  • C. Bogleråsen
    Bogleråsen is a residential neighborhood located in the Østensjø borough of Oslo, Norway.
  • D. Ågotnes
    Ågotnes is a village and industrial hub on the island of Sotra in Vestland county, Norway.
  • E. Vågå
    Vågå is a rural municipality in Innlandet county, Norway, known for its traditional farming landscape, historic stave church, and proximity to the Jotunheimen mountain area.
  • 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_69ca84cc78808190a56f3402b7c139a7 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d70f55c8190934f37c25e9d4ba4 completed April 1, 2026, 10:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1912e645881908d223a93f3ee61da completed April 4, 2026, 10:31 p.m.
NEDg Description generation batch_69d191ea02e8819097e5a4247a8084f6 completed April 4, 2026, 10:34 p.m.
NED2 Entity disambiguation (via description) batch_69d19251095881909272c53c026b2ad1 completed April 4, 2026, 10:36 p.m.
Created at: March 30, 2026, 8:18 p.m.