Triple

T11540709
Position Surface form Disambiguated ID Type / Status
Subject Call of Duty 4: Modern Warfare E273665 entity
Predicate gameEngine P26587 FINISHED
Object IW engine E266240 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: IW engine | Statement: [Call of Duty 4: Modern Warfare, gameEngine, IW engine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IW engine
Context triple: [Call of Duty 4: Modern Warfare, gameEngine, IW engine]
  • A. IW engine chosen
    The IW engine is a proprietary game engine developed by Infinity Ward and used across multiple Call of Duty titles, including those created by Treyarch.
  • B. IW 2.0
    IW 2.0 is a specific release of the IW engine software, representing an updated iteration with improvements and new features over earlier versions.
  • C. IW
    IW is the common abbreviation for Infinity Ward, a prominent video game developer best known for creating the Call of Duty franchise.
  • D. Void Engine
    Void Engine is a proprietary game engine developed by Arkane Studios, known for powering visually rich, immersive first-person games like Dishonored 2 and Deathloop.
  • E. BI Engine
    BI Engine is an in-memory analysis service for Google BigQuery that accelerates and optimizes interactive business intelligence and dashboard queries.
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d886deed5c81908e5c38156064f882 completed April 10, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69e7137a09608190801af2125e2e8095 completed April 21, 2026, 6:04 a.m.
Created at: April 8, 2026, 9:37 p.m.