Triple

T3443103
Position Surface form Disambiguated ID Type / Status
Subject YleX E72609 entity
Predicate hasSisterStation P15137 FINISHED
Object Yle Radio Suomi E74194 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: Yle Radio Suomi | Statement: [YleX, hasSisterStation, Yle Radio Suomi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yle Radio Suomi
Context triple: [YleX, hasSisterStation, Yle Radio Suomi]
  • A. Yle Radio Suomi chosen
    Yle Radio Suomi is Finland’s largest national radio channel, offering news, current affairs, culture, and entertainment programming in Finnish to audiences across the country.
  • B. Yleisradio
    Yleisradio is Finland’s national public broadcasting company, providing television, radio, and online services funded primarily by public means.
  • C. Yle Puhe
    Yle Puhe is a Finnish Yle radio channel focused on talk programming, including news, current affairs, culture, and in-depth discussions.
  • D. Yle TV
    Yle TV is Finland’s national public television broadcaster, operated by the Finnish Broadcasting Company (Yleisradio).
  • E. Yle Uutiset
    Yle Uutiset is the main news service of Finland’s public broadcaster, providing national and international news across television, radio, and digital platforms.
  • 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_69ad85b05c848190b7a28ceec2bd7b74 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adba2a605c8190a0eafdf6f25b1e38 completed March 8, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4881f1e1c81908de3a0729761c4f7 completed March 13, 2026, 9:56 p.m.
Created at: March 8, 2026, 3:16 p.m.