Triple

T20165583
Position Surface form Disambiguated ID Type / Status
Subject Contra E491817 entity
Predicate platform P1292 FINISHED
Object ZX Spectrum 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: ZX Spectrum | Statement: [Contra, platform, ZX Spectrum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ZX Spectrum
Context triple: [Contra, platform, ZX Spectrum]
  • A. ZX Spectrum chosen
    The ZX Spectrum is an 8-bit home computer released by Sinclair Research in 1982, famous for its rubber keyboard, distinctive color graphics, and major role in the rise of home computing and gaming in the UK.
  • B. Amstrad CPC
    The Amstrad CPC is an 8-bit home computer line from the 1980s, popular in Europe for gaming and productivity software.
  • C. Amstrad
    Amstrad is a British electronics company best known for its affordable home computers and consumer electronics that were popular in the 1980s and 1990s.
  • D. BBC Micro
    The BBC Micro was a popular 1980s British home and educational computer, widely used in schools and influential in early personal computing and programming education in the UK.
  • E. ZX81
    The ZX81 is a low-cost home computer developed by Sinclair Research in the early 1980s, notable for popularizing personal computing in the UK before the rise of more advanced systems.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e668442d2c81908bb1a0fac9895b5e completed April 20, 2026, 5:54 p.m.
Created at: April 11, 2026, 11:35 p.m.