Triple

T38309337
Position Surface form Disambiguated ID Type / Status
Subject AMD Instinct MI100 E1033641 entity
Predicate peakFP32Performance P33100 FINISHED
Object 23.1 TFLOPS 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: 23.1 TFLOPS | Statement: [AMD Instinct MI100, peakFP32Performance, 23.1 TFLOPS]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: peakFP32Performance
Context triple: [AMD Instinct MI100, peakFP32Performance, 23.1 TFLOPS]
  • A. floatingPointPerformance
    Indicates the level of computational capability or efficiency an entity has when performing floating-point arithmetic operations.
  • B. 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.
  • C. numberOfFloatingPointUnits
    Indicates the quantity of floating-point processing units associated with or contained in an entity.
  • D. gpuComputePerformance chosen
    Indicates the level of processing capability a GPU can deliver for computational tasks, typically measured in operations per unit time.
  • E. floatingPointRegisterCount
    Indicates the number of floating-point registers associated with an entity (such as a processor or execution context).
  • 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_69f76e132c408190969b3d35c04b87ae completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69fcd1499e2c81909bafd84dc4810f45 completed May 7, 2026, 5:52 p.m.
PD Predicate disambiguation batch_69fcccf024ec819086383ffbb6cfc036 completed May 7, 2026, 5:33 p.m.
Created at: May 3, 2026, 4:30 p.m.