Triple

T20399541
Position Surface form Disambiguated ID Type / Status
Subject SGI Indy E500294 entity
Predicate architecture P4621 FINISHED
Object MIPS NE NERFINISHED

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: MIPS | Statement: [SGI Indy, architecture, MIPS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MIPS
Context triple: [SGI Indy, architecture, MIPS]
  • A. MIPS
    MIPS is an infrared imaging and photometry instrument that operated aboard the Spitzer Space Telescope, used to study celestial objects at multiple mid- to far-infrared wavelengths.
  • B. MIPS chosen
    MIPS is a RISC (Reduced Instruction Set Computer) processor architecture widely used in embedded systems, networking equipment, and academic settings.
  • C. MIPS II
    MIPS II is the second-generation version of the MIPS instruction set architecture, extending the original design with additional instructions and features for improved performance and functionality.
  • D. MIPS III
    MIPS III is a 64-bit RISC instruction set architecture in the MIPS family, extending earlier versions with larger address space and enhanced computational capabilities.
  • E. MIPS R2000
    The MIPS R2000 is an early 32-bit RISC microprocessor that helped popularize the MIPS architecture in academic and commercial systems during the late 1980s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798cf04481909f183c4c75fe6d52 completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:29 a.m.