Triple

T576663
Position Surface form Disambiguated ID Type / Status
Subject ARM E13771 entity
Predicate hasExtension P455 FINISHED
Object VFP floating-point extension
The VFP floating-point extension is an ARM architecture coprocessor feature that provides hardware support for high-performance single- and double-precision floating-point arithmetic.
 E72125 NE FINISHED

How this triple was built (4 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: VFP floating-point extension | Statement: [ARM, hasExtension, VFP floating-point extension]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: VFP floating-point extension
Context triple: [ARM, hasExtension, VFP floating-point extension]
  • A. IEEE 754 floating‑point arithmetic standard
    The IEEE 754 floating‑point arithmetic standard is the globally adopted specification that defines formats and rules for representing and performing binary and decimal floating‑point calculations in computer systems.
  • B. VMX
    VMX is a vector processing extension to the PowerPC architecture designed to accelerate multimedia, signal processing, and other parallelizable computations.
  • C. AltiVec
    AltiVec is a vector processing extension for the PowerPC architecture that accelerates multimedia, signal processing, and other parallelizable computations.
  • D. VFAT
    VFAT is a Linux-compatible variant of the FAT file system that adds support for long filenames and improved interoperability with Windows systems.
  • E. NVIDIA CUDA
    NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: VFP floating-point extension
Triple: [ARM, hasExtension, VFP floating-point extension]
Generated description
The VFP floating-point extension is an ARM architecture coprocessor feature that provides hardware support for high-performance single- and double-precision floating-point arithmetic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: VFP floating-point extension
Target entity description: The VFP floating-point extension is an ARM architecture coprocessor feature that provides hardware support for high-performance single- and double-precision floating-point arithmetic.
  • A. IEEE 754 floating‑point arithmetic standard
    The IEEE 754 floating‑point arithmetic standard is the globally adopted specification that defines formats and rules for representing and performing binary and decimal floating‑point calculations in computer systems.
  • B. VMX
    VMX is a vector processing extension to the PowerPC architecture designed to accelerate multimedia, signal processing, and other parallelizable computations.
  • C. AltiVec
    AltiVec is a vector processing extension for the PowerPC architecture that accelerates multimedia, signal processing, and other parallelizable computations.
  • D. VFAT
    VFAT is a Linux-compatible variant of the FAT file system that adds support for long filenames and improved interoperability with Windows systems.
  • E. NVIDIA CUDA
    NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
  • F. None of above. chosen

Provenance (5 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_69a4933fa4d88190a7949cc83c08c5c1 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49b68cc808190b1ba45bdad78443d completed March 1, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4ff4db0248190b2b3ca0290467313 completed March 2, 2026, 3:09 a.m.
NEDg Description generation batch_69a500891de4819086b4599fb4ee328c completed March 2, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_69a5010c65a881908cce2e1a3d9f158d completed March 2, 2026, 3:16 a.m.
Created at: March 1, 2026, 7:33 p.m.