Triple

T17032257
Position Surface form Disambiguated ID Type / Status
Subject Ruisrock E413227 entity
Predicate locatedOn P40 FINISHED
Object island of Ruissalo
The island of Ruissalo is a scenic island in Turku, Finland, known for its lush oak forests, historic villas, and popular recreational areas.
E1247899 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: island of Ruissalo | Statement: [Ruisrock, locatedOn, island of Ruissalo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: island of Ruissalo
Context triple: [Ruisrock, locatedOn, island of Ruissalo]
  • A. Susisaari
    Susisaari is one of the main islands that make up the historic Suomenlinna sea fortress off the coast of Helsinki, Finland.
  • B. Louhisaari
    Louhisaari is a historic manor estate in Askainen, Finland, best known as the birthplace of Finnish President Carl Gustaf Emil Mannerheim and for its well-preserved 17th-century architecture.
  • C. Siltasaari
    Siltasaari is a central district of Helsinki, Finland, known for its urban waterfront setting and role as a key traffic and commercial hub.
  • D. Pietarsaari
    Pietarsaari is a bilingual coastal town in western Finland known for its historic wooden architecture and maritime heritage.
  • E. Tammisaari
    Tammisaari is a historic coastal town in southern Finland, known for its well-preserved wooden old town and seaside setting.
  • 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: island of Ruissalo
Triple: [Ruisrock, locatedOn, island of Ruissalo]
Generated description
The island of Ruissalo is a scenic island in Turku, Finland, known for its lush oak forests, historic villas, and popular recreational areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: island of Ruissalo
Target entity description: The island of Ruissalo is a scenic island in Turku, Finland, known for its lush oak forests, historic villas, and popular recreational areas.
  • A. Susisaari
    Susisaari is one of the main islands that make up the historic Suomenlinna sea fortress off the coast of Helsinki, Finland.
  • B. Louhisaari
    Louhisaari is a historic manor estate in Askainen, Finland, best known as the birthplace of Finnish President Carl Gustaf Emil Mannerheim and for its well-preserved 17th-century architecture.
  • C. Siltasaari
    Siltasaari is a central district of Helsinki, Finland, known for its urban waterfront setting and role as a key traffic and commercial hub.
  • D. Pietarsaari
    Pietarsaari is a bilingual coastal town in western Finland known for its historic wooden architecture and maritime heritage.
  • E. Tammisaari
    Tammisaari is a historic coastal town in southern Finland, known for its well-preserved wooden old town and seaside setting.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8ed79448190a750a29a99913fda completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012336cfd481909f93c6ea7c94b49f completed May 11, 2026, 12:30 a.m.
NEDg Description generation batch_6a01259ebc748190a9ba5b1ccfb13210 completed May 11, 2026, 12:41 a.m.
NED2 Entity disambiguation (via description) batch_6a0125fed58881909218c7534f9dc8c8 completed May 11, 2026, 12:42 a.m.
Created at: April 10, 2026, 5:33 a.m.