Triple

T13815441
Position Surface form Disambiguated ID Type / Status
Subject Helsinki region E332002 entity
Predicate contains P35 FINISHED
Object Lohja E212980 NE FINISHED

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: Lohja | Statement: [Helsinki region, contains, Lohja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lohja
Context triple: [Helsinki region, contains, Lohja]
  • A. Lohja chosen
    Lohja is a town and municipality in southern Finland known for its lakes, limestone industry, and location within the Uusimaa region.
  • B. Loviisa
    Loviisa is a small coastal town and municipality in southern Finland known for its historic wooden houses, seaside location, and nuclear power plant.
  • C. Ruokolahti
    Ruokolahti is a rural municipality in South Karelia, southeastern Finland, known for its lake-rich landscapes and proximity to the Russian border.
  • D. Kuokkala
    Kuokkala is a former Finnish locality on the Karelian Isthmus, now known as Repino in Saint Petersburg, Russia.
  • E. Kuokkala
    Kuokkala is a residential district of the city of Jyväskylä in central Finland, known for its lakeside location and distinctive bridge connection to the city center.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d81c59f8808190a851bc56afdc55e9 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02806e148190996f58934e66d7d8 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8e0112481909deb31f8614f8b93 completed May 3, 2026, 9:06 p.m.
Created at: April 9, 2026, 10:12 p.m.