Triple

T2108140
Position Surface form Disambiguated ID Type / Status
Subject PlayStation 4 E42441 entity
Predicate manufacturer P490 FINISHED
Object Sony Computer Entertainment E6422 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: Sony Computer Entertainment | Statement: [PlayStation 4, manufacturer, Sony Computer Entertainment]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sony Computer Entertainment
Context triple: [PlayStation 4, manufacturer, Sony Computer Entertainment]
  • A. Sony chosen
    Sony is a Japanese multinational conglomerate best known for its consumer electronics, gaming (PlayStation), entertainment, and imaging products.
  • B. Nintendo
    Nintendo is a Japanese video game company best known for creating iconic franchises such as Mario, The Legend of Zelda, and Pokémon, as well as popular gaming consoles like the Nintendo Switch.
  • C. Toyopa Group, LLC
    Toyopa Group, LLC is the original corporate name under which the company now known as Snap Inc., the parent of Snapchat, was first established.
  • D. Sega
    Sega is a Japanese video game and entertainment company best known for its iconic consoles and franchises such as Sonic the Hedgehog.
  • E. Midway Games
    Midway Games was an American video game company best known for publishing and developing popular arcade and console titles such as the Mortal Kombat series.
  • 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_69a8871040f08190aac2e2d0ab6b47ad completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbae03f308190841f5a419bb821f6 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69b261a163a08190bd5bdb95725e4072 completed March 12, 2026, 6:48 a.m.
Created at: March 4, 2026, 7:43 p.m.