Triple

T3778234
Position Surface form Disambiguated ID Type / Status
Subject MyGM mode E83358 entity
Predicate developer P73 FINISHED
Object Visual Concepts E83354 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: Visual Concepts | Statement: [MyGM mode, developer, Visual Concepts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Visual Concepts
Context triple: [MyGM mode, developer, Visual Concepts]
  • A. Visual Concepts chosen
    Visual Concepts is a video game development studio best known for creating the long-running NBA 2K basketball simulation series.
  • B. Visual Component Library
    Visual Component Library is Delphi’s native GUI framework that provides a rich set of reusable visual and non-visual components for building Windows applications.
  • C. Vision and Design
    Vision and Design is an influential collection of art criticism essays by Roger Fry that helped shape modernist art theory and appreciation in the early 20th century.
  • D. Vision
    Vision is a powerful, synthetically created superhero in the Marvel universe known for his android body, advanced intellect, and moral complexity.
  • E. Vision
    Vision is Apple’s mixed-reality product line centered on advanced spatial computing headsets like the Apple Vision Pro.
  • 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_69ad8b235e608190b5a2b1d1bfcef50b completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcc78173081908b230017834cdf9e completed March 8, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb1616008190a6ec9a2df5bac2b4 completed March 14, 2026, 6:07 a.m.
Created at: March 8, 2026, 3:36 p.m.