Triple

T11778389
Position Surface form Disambiguated ID Type / Status
Subject Halo 2 E280075 entity
Predicate gameEngine P26587 FINISHED
Object Blam engine E738590 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: Blam engine | Statement: [Halo 2, gameEngine, Blam engine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blam engine
Context triple: [Halo 2, gameEngine, Blam engine]
  • A. Blam! engine chosen
    The Blam! engine is the proprietary game engine developed by Bungie that powered the early Halo titles, enabling their large-scale environments, AI, and physics.
  • B. Aurora Engine
    Aurora Engine is a role-playing game engine developed by BioWare, best known for powering classic titles like Neverwinter Nights.
  • C. Paradox Engine
    Paradox Engine is a powerful artifact card from Magic: The Gathering that untaps all nonland permanents you control whenever you cast a spell, enabling highly explosive combo turns.
  • D. Tempest Engine
    Tempest Engine is Sony’s dedicated 3D audio processing hardware used in the PlayStation 5 to deliver immersive, spatial sound in games.
  • E. LithTech
    LithTech is a proprietary 3D game engine originally developed by Monolith Productions and used to power numerous first-person shooters and action games.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a560bf548190afab3ad14f953a71 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f090b8f4c481908cb3cf03875c0e24 completed April 28, 2026, 10:49 a.m.
Created at: April 8, 2026, 9:42 p.m.