Triple

T1837063
Position Surface form Disambiguated ID Type / Status
Subject Finnish Navy E41089 entity
Predicate garrison P75 FINISHED
Object Oulu E128725 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: Oulu | Statement: [Finnish Navy, garrison, Oulu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oulu
Context triple: [Finnish Navy, garrison, Oulu]
  • A. Oulu chosen
    Oulu is a major city in northern Finland known for its technology industry, university, and position near the Gulf of Bothnia.
  • B. Kokkola
    Kokkola is a coastal city in western Finland known for its maritime heritage and role as a military and naval hub.
  • C. Lahti
    Lahti is a city in southern Finland known for its winter sports facilities, particularly ski jumping and cross-country skiing, and for hosting numerous international sporting events.
  • D. Pori
    Pori is a coastal city in western Finland known for its industrial heritage, port, and annual Pori Jazz Festival.
  • E. Joensuu
    Joensuu is a city in eastern Finland that serves as a regional center for North Karelia, known for its university, forestry industry, and proximity to lakes and forests.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0380a4c81909a2ad0bfd97c884a completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69af9040c20c8190aaae6f22fc893032 completed March 10, 2026, 3:30 a.m.
Created at: March 4, 2026, 7:33 p.m.