Triple

T18472228
Position Surface form Disambiguated ID Type / Status
Subject Kalevi Sorsa E451329 entity
Predicate workLocation P7 FINISHED
Object Helsinki, Finland NE NERFINISHED

How this triple was built (2 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: Helsinki, Finland | Statement: [Kalevi Sorsa, workLocation, Helsinki, Finland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helsinki, Finland
Context triple: [Kalevi Sorsa, workLocation, Helsinki, Finland]
  • A. Helsinki chosen
    Helsinki is the capital and largest city of Finland, known for its coastal location on the Baltic Sea, modern design, and vibrant cultural life.
  • B. Espoo, Finland
    Espoo, Finland is a major city in the Helsinki metropolitan area known as a technology and innovation hub that has long hosted the corporate headquarters of Nokia.
  • C. 42 Helsinki
    42 Helsinki is a Finnish campus of the global, tuition-free 42 coding school network, offering peer-to-peer, project-based software engineering education.
  • D. Vantaa, Finland
    Vantaa, Finland is a major city in the Helsinki metropolitan area best known for hosting Helsinki Airport and serving as an important transportation and commercial hub.
  • E. Kluuvi, Helsinki
    Kluuvi, Helsinki is a central district of Finland’s capital city, known as a key commercial and cultural hub that includes major shopping streets, offices, and university buildings.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d38465a0819099b9b42d2a662ac1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53060ae2c8190bf0821bb0ea5bd59 completed April 19, 2026, 7:43 p.m.
Created at: April 10, 2026, 11:34 a.m.