Triple

T9027100
Position Surface form Disambiguated ID Type / Status
Subject Intel SSE E216074 entity
Predicate predecessor P97 FINISHED
Object Intel MMX E643844 NE 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: Intel MMX | Statement: [Intel SSE, predecessor, Intel MMX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Intel MMX
Context triple: [Intel SSE, predecessor, Intel MMX]
  • A. Intel SSE
    Intel SSE is a set of SIMD (Single Instruction, Multiple Data) instruction extensions for x86 processors designed to accelerate multimedia, gaming, and scientific applications through parallel data processing.
  • B. 3DNow!
    3DNow! is a SIMD instruction set extension developed by AMD to accelerate floating-point and multimedia processing, particularly for 3D graphics and gaming workloads.
  • C. MMX
    MMX (Martian Moons eXploration) is a JAXA-led space mission designed to explore Mars’s moons, particularly Phobos, and return samples to Earth for detailed analysis.
  • D. MMX chosen
    MMX is an Intel multimedia extension technology that adds SIMD instructions to accelerate tasks like audio, video, and graphics processing on compatible processors.
  • E. Intel AVX
    Intel AVX is an x86 processor instruction set extension from Intel that accelerates floating-point and vector-intensive workloads, commonly used in high-performance computing, multimedia, and scientific applications.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca83a5fa88819088144801b4dd7245 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6a7eb5b881908ace0c3327f06161 completed April 1, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbbf786081908df45b4e615bbba9 completed April 3, 2026, 3:24 p.m.
Created at: March 30, 2026, 7:07 p.m.