Triple

T10656182
Position Surface form Disambiguated ID Type / Status
Subject SVT Play E251092 entity
Predicate partOf P40 FINISHED
Object Sveriges Television online services E51238 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: Sveriges Television online services | Statement: [SVT Play, partOf, Sveriges Television online services]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sveriges Television online services
Context triple: [SVT Play, partOf, Sveriges Television online services]
  • A. Sveriges Television chosen
    Sveriges Television is Sweden's national public television broadcaster, known for producing and airing a wide range of news, cultural, and entertainment programming.
  • B. Viaplay
    Viaplay is a Nordic-based streaming service specializing in sports, films, and TV series, known for its live sports coverage across Europe.
  • C. Svt
    Svt is the station code for Strandvliet, a metro station in Amsterdam, Netherlands.
  • D. TV3 (Sweden)
    TV3 (Sweden) is a Swedish commercial television channel known for broadcasting entertainment programming, including reality shows and imported series.
  • E. ES.TV
    ES.TV is an entertainment-focused television network and media brand known for celebrity interviews, movie-related content, and pop culture programming.
  • 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dffa73a08190bf661df600b4ab96 completed April 8, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d97a7aa490819094c7eaf3fc5e2c43 completed April 10, 2026, 10:32 p.m.
Created at: April 8, 2026, 9:07 p.m.