Triple

T21627519
Position Surface form Disambiguated ID Type / Status
Subject ZX Spectrum E533740 entity
Predicate hasNickname P39 FINISHED
Object Speccy 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: Speccy | Statement: [ZX Spectrum, hasNickname, Speccy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Speccy
Context triple: [ZX Spectrum, hasNickname, Speccy]
  • A. Speccy chosen
    Speccy is a popular nickname for the ZX Spectrum, an iconic 1980s 8-bit home computer known for its distinctive rubber keyboard and influential role in early video gaming and home computing.
  • B. Speccy
    Speccy is a system information tool by Piriform that provides detailed hardware and software specifications for Windows computers.
  • C. CCleaner
    CCleaner is a popular utility software that cleans and optimizes computers by removing unnecessary files, managing startup programs, and improving system performance and privacy.
  • D. Defraggler
    Defraggler is a disk defragmentation utility for Windows that allows users to optimize and reorganize files on their hard drives for improved performance.
  • E. Armoury Chamber
    The Armoury Chamber is a historic museum within Moscow's Kremlin that houses Russia's most treasured state regalia, ceremonial weapons, jewelry, and artifacts.
  • 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_69e0c464fba881908d0ff2ac80511ce1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef52141e1c8190a861f4bc7cfcb490 completed April 27, 2026, 12:09 p.m.
Created at: April 16, 2026, 6:34 p.m.