Triple

T18016312
Position Surface form Disambiguated ID Type / Status
Subject MobileNetV2 E431005 entity
Predicate FLOPs P64004 FINISHED
Object approximately 300 million multiply-adds (1.0 width, 224x224) LITERAL 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: approximately 300 million multiply-adds (1.0 width, 224x224) | Statement: [MobileNetV2, FLOPs, approximately 300 million multiply-adds (1.0 width, 224x224)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: FLOPs
Context triple: [MobileNetV2, FLOPs, approximately 300 million multiply-adds (1.0 width, 224x224)]
  • A. numberOfFloatingPointUnits
    Indicates the quantity of floating-point processing units associated with or contained in an entity.
  • B. floatingPointPerformance
    Indicates the level of computational capability or efficiency an entity has when performing floating-point arithmetic operations.
  • C. FPU
    Indicates that one entity functions as or contains a floating-point unit responsible for performing arithmetic operations on non-integer (floating-point) numbers for another entity or within a system.
  • D. neuralEnginePerformance
    Indicates the level or efficiency of processing capability provided by a neural engine in performing AI or machine-learning tasks.
  • E. computationalCost chosen
    Indicates the amount of computing resources (such as time, memory, or processing power) required to perform a given operation or process.
  • F. None of above.

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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b523f588819097389e067dda7f23 completed April 19, 2026, 10:57 a.m.
PD Predicate disambiguation batch_69e3f904b8048190add43883cd7cb191 completed April 18, 2026, 9:35 p.m.
Created at: April 10, 2026, 10:24 a.m.