Triple

T18305649
Position Surface form Disambiguated ID Type / Status
Subject Kymi River E438475 entity
Predicate passesThrough P225 FINISHED
Object Iitti 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: Iitti | Statement: [Kymi River, passesThrough, Iitti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iitti
Context triple: [Kymi River, passesThrough, Iitti]
  • A. Iitti chosen
    Iitti is a small municipality in southern Finland known for its rural landscapes and proximity to major urban centers like the Greater Helsinki area.
  • B. Siili
    Siili is a residential subdistrict within the Mustamäe district of Tallinn, Estonia.
  • C. Kannin
    Kannin was a Japanese imperial era name (nengō) used during the reign of Emperor Go-Ichijō in the early 11th century.
  • D. Kattavia
    Kattavia is a small traditional village located at the southern tip of the Greek island of Rhodes, known for its quiet atmosphere and proximity to popular windsurfing beaches.
  • E. Pertteli
    Pertteli was a former municipality in southwestern Finland that is now part of the city of Salo.
  • 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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50183394081909b86cefaaa0a3aa8 completed April 19, 2026, 4:23 p.m.
Created at: April 10, 2026, 10:35 a.m.