Triple

T6960404
Position Surface form Disambiguated ID Type / Status
Subject Decima E161353 entity
Predicate developer P73 FINISHED
Object Guerrilla Games E631067 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: Guerrilla Games | Statement: [Decima, developer, Guerrilla Games]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guerrilla Games
Context triple: [Decima, developer, Guerrilla Games]
  • A. Guerrilla Games chosen
    Guerrilla Games is a Dutch video game developer best known for creating the Horizon and Killzone franchises.
  • B. Remedy Entertainment
    Remedy Entertainment is a Finnish video game developer best known for story-driven action titles such as Max Payne, Alan Wake, and Control.
  • C. Insomniac Games
    Insomniac Games is an American video game developer best known for creating acclaimed franchises such as Spyro the Dragon, Ratchet & Clank, and Marvel’s Spider-Man.
  • D. Tango Gameworks
    Tango Gameworks is a Japanese video game development studio best known for creating the survival horror series The Evil Within and the action-adventure game Ghostwire: Tokyo.
  • E. Swordfish Studios
    Swordfish Studios was a British video game development company known for creating titles such as World Championship Rugby and 50 Cent: Blood on the Sand.
  • 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6daeee4d48190b078beeebb0053f4 completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a00ded081908db2a4d539e4e502 completed March 28, 2026, 5:41 a.m.
Created at: March 27, 2026, 2:29 p.m.