Triple

T36165732
Position Surface form Disambiguated ID Type / Status
Subject NDAs (New Desk Accessories) E1045991 entity
Predicate supportsMultitaskingStyle P31924 FINISHED
Object cooperative multitasking within GS/OS LITERAL 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: cooperative multitasking within GS/OS | Statement: [NDAs (New Desk Accessories), supportsMultitaskingStyle, cooperative multitasking within GS/OS]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: supportsMultitaskingStyle
Context triple: [NDAs (New Desk Accessories), supportsMultitaskingStyle, cooperative multitasking within GS/OS]
  • A. multitaskingSupport
    Indicates that an entity is capable of performing multiple tasks or operations concurrently or in parallel.
  • B. multitaskingType chosen
    Indicates the specific way in which multiple tasks or activities are performed or managed concurrently in a given context.
  • C. supportsMultitaskingOfDOSPrograms
    Indicates that a system or environment is capable of running and managing multiple DOS programs simultaneously.
  • D. supportsMultiprogramming
    Indicates that a system, component, or environment is capable of executing or managing multiple programs or processes concurrently.
  • E. supportsMultipleWindows
    Indicates that the subject can handle or display more than one window or view simultaneously.
  • F. None of above.

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_69f76e396bc88190b99d221bff9be27a completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a037c8d06cc8190ab6a5e18d9d2571e completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a037a0895b48190acdd88dc10db7be7 completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:08 p.m.