Triple

T7885452
Position Surface form Disambiguated ID Type / Status
Subject BlackBerry Limited E183090 entity
Predicate hasKeyFocusArea P10167 FINISHED
Object cybersecurity software 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: cybersecurity software | Statement: [BlackBerry Limited, hasKeyFocusArea, cybersecurity software]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasKeyFocusArea
Context triple: [BlackBerry Limited, hasKeyFocusArea, cybersecurity software]
  • A. hasAccessibilityFocus
    Indicates that a user interface element is currently the primary target of accessibility tools, such as screen readers or keyboard navigation, receiving focused attention for interaction.
  • B. hasPrimaryFocus chosen
    Indicates that something is the main subject, concern, or area of attention for an entity or activity.
  • C. hasGlobalFocus
    Indicates that something is oriented toward, concerned with, or applicable to worldwide or international scope rather than a local or regional one.
  • D. hasProgramFocus
    Indicates that an entity (such as a program or initiative) is oriented around or primarily concerned with a particular thematic area, topic, or objective.
  • E. hasActingFocus
    Indicates that an entity is the primary performer or focal agent carrying out an action in a given context.
  • 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_69ca828af6e48190a06ee7010d8f0e64 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39d62a148190bed4e0d199aa427b completed March 31, 2026, 3:04 a.m.
PD Predicate disambiguation batch_69cae92b0cd881908e715a10d3252e83 completed March 30, 2026, 9:20 p.m.
Created at: March 30, 2026, 4:59 p.m.