Triple

T865989
Position Surface form Disambiguated ID Type / Status
Subject HBO E18702 entity
Predicate competitor P1375 FINISHED
Object Amazon Prime Video E21778 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: Amazon Prime Video | Statement: [HBO, competitor, Amazon Prime Video]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amazon Prime Video
Context triple: [HBO, competitor, Amazon Prime Video]
  • A. Amazon Prime Video chosen
    Amazon Prime Video is a subscription-based streaming service from Amazon that offers a wide range of movies, TV series, and original content available on-demand across multiple devices.
  • B. Paramount+
    Paramount+ is a subscription-based streaming service from Paramount Global that offers live sports, original series, and a wide range of on-demand TV shows and movies.
  • C. Hulu
    Hulu is a U.S.-based subscription streaming service offering on-demand access to a wide range of television shows, films, and original content.
  • D. Disney+
    Disney+ is a subscription-based streaming service from The Walt Disney Company that offers movies and TV shows from Disney, Pixar, Marvel, Star Wars, National Geographic, and more.
  • E. Apple TV+
    Apple TV+ is Apple’s subscription-based streaming platform offering original TV series, films, and documentaries across its devices and the web.
  • 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_69a4938ce8688190a24bdfef82ba7d21 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac7cb1888190a46c16b30256451b completed March 1, 2026, 9:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7b84dcf748190b20372fdc48d6766 completed March 4, 2026, 4:42 a.m.
Created at: March 1, 2026, 7:39 p.m.