Triple

T4062306
Position Surface form Disambiguated ID Type / Status
Subject Sky Italia E86240 entity
Predicate hasService P182 FINISHED
Object Sky Go E72561 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: Sky Go | Statement: [Sky Italia, hasService, Sky Go]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sky Go
Context triple: [Sky Italia, hasService, Sky Go]
  • A. Sky Go chosen
    Sky Go is a streaming and on-demand television service that allows Sky customers in the UK and Ireland to watch live and catch-up content on various internet-connected devices.
  • B. Sky Player
    Sky Player was the earlier online television streaming service from Sky in the UK, later rebranded as Sky Go.
  • C. Periscope
    Periscope was a live video streaming mobile app that allowed users to broadcast and watch real-time video from around the world.
  • D. Sky Q
    Sky Q is a premium television and entertainment platform from Sky that offers multi-room viewing, on-demand content, and integrated streaming services.
  • E. Roku
    Roku is a popular digital media player platform that streams internet-based television, movies, and other content through apps and channels on connected TVs.
  • 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_69aed93c69208190a4efac0efe3cd69b completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefbd60cc081908764fcc8206bc1ef completed March 9, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b562ac25848190951431c9c853cc59 completed March 14, 2026, 1:29 p.m.
Created at: March 9, 2026, 3:38 p.m.