Triple

T18704574
Position Surface form Disambiguated ID Type / Status
Subject SiFive E457337 entity
Predicate architectureUsed P4621 FINISHED
Object RISC-V NE NERFINISHED

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: RISC-V | Statement: [SiFive, architectureUsed, RISC-V]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RISC-V
Context triple: [SiFive, architectureUsed, RISC-V]
  • A. RISC-V chosen
    RISC-V is an open, extensible instruction set architecture (ISA) based on the reduced instruction set computing (RISC) principles, widely used for research, embedded systems, and increasingly general-purpose computing.
  • B. RISC-V International
    RISC-V International is the global nonprofit consortium that oversees the development, standardization, and promotion of the open RISC-V instruction set architecture.
  • C. SiFive
    SiFive is a semiconductor company known for designing customizable RISC‑V processor cores and platforms used in a wide range of computing applications.
  • D. Spike RISC-V ISA simulator
    Spike RISC-V ISA simulator is the official reference software simulator for the RISC-V instruction set architecture, used to validate and test RISC-V implementations.
  • E. RISC
    RISC is an Austrian research institute specializing in symbolic computation, computer algebra, and related areas of mathematics and computer science.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: architectureUsed
Context triple: [SiFive, architectureUsed, RISC-V]
  • A. architectureName
    Indicates the specific name or title assigned to an architecture.
  • B. architectureType
    Indicates the specific style or category of architecture that characterizes or defines an entity.
  • C. architectureCanUse
    Indicates that a particular architecture is capable of employing, incorporating, or being built with a specified component, technique, or resource.
  • D. architecture chosen
    Indicates the structural design or organizational framework that defines how components of a system or entity are arranged and interact.
  • E. architecturalUse
    Indicates how a structure, space, or element is intended to be used or function within an architectural 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671665bc8190b9b4a4ce4ec5b2eb completed April 19, 2026, 11:36 p.m.
PD Predicate disambiguation batch_69e478de85088190ba5f005f1d39f587 completed April 19, 2026, 6:40 a.m.
Created at: April 10, 2026, 11:49 a.m.