Triple

T35053643
Position Surface form Disambiguated ID Type / Status
Subject Emotion Engine E1011399 entity
Predicate vectorUnit P182054 FINISHED
Object VU0
VU0 is one of the PlayStation 2’s specialized vector processing units in the Emotion Engine, optimized for fast 3D geometry and graphics-related calculations.
 E2124993 NE FINISHED

How this triple was built (3 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: VU0 | Statement: [Emotion Engine, vectorUnit, VU0]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: VU0
Triple: [Emotion Engine, vectorUnit, VU0]
Generated description
VU0 is one of the PlayStation 2’s specialized vector processing units in the Emotion Engine, optimized for fast 3D geometry and graphics-related calculations.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: vectorUnit
Context triple: [Emotion Engine, vectorUnit, VU0]
  • A. vector
    Indicates that one entity is a vector associated with, representing, or characterizing another entity (such as a quantity with magnitude and direction, or a carrier/representative of something).
  • B. isVectorMagnitudeUnit
    Indicates that a given unit is used to measure the magnitude (size or length) of a vector quantity.
  • C. vectorLength
    Indicates the numerical magnitude or size of a vector, typically computed from its components.
  • D. vectorType
    Indicates that one entity is classified as the type or category of vector associated with another entity.
  • E. secondUnitDirected
    Indicates that the second unit in a pair is the one toward which an action, orientation, or directive is specifically aimed or directed.
  • F. None of above. chosen

Provenance (7 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_69f76dcfdda48190b1ebae5da8b54f12 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f7865578d48190bf90e470634fd97d completed May 3, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a37c637b0c08190a4e9a3ced4c62790 completed June 21, 2026, 11:08 a.m.
NEDg Description generation batch_6a37c6e970f48190b35c179e766c58cc completed June 21, 2026, 11:11 a.m.
NED2 Entity disambiguation (via description) batch_6a37cad6f71c81908794928c0e20ab20 completed June 21, 2026, 11:28 a.m.
PD Predicate disambiguation batch_69f7841812f081909d878955d114088e completed May 3, 2026, 5:21 p.m.
PDg Predicate description generation batch_69f78575917481909a3defd6a4c366bd completed May 3, 2026, 5:27 p.m.
Created at: May 3, 2026, 4:01 p.m.