Triple

T14538910
Position Surface form Disambiguated ID Type / Status
Subject QNX E341120 entity
Predicate developer P73 FINISHED
Object BlackBerry Limited E183090 NE 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: BlackBerry Limited | Statement: [QNX, developer, BlackBerry Limited]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BlackBerry Limited
Context triple: [QNX, developer, BlackBerry Limited]
  • A. BlackBerry Limited chosen
    BlackBerry Limited is a Canadian technology company best known for its pioneering smartphones and secure communications software.
  • B. Blackberry
    Blackberry is a dark purple-black fruit of the Rubus genus, commonly found in hedgerows and used in foods like jams, desserts, and wines.
  • C. Motorola Mobility
    Motorola Mobility is a consumer electronics company best known for designing and manufacturing Android smartphones and smartwatches, including devices running Google's Wear OS platform.
  • D. Nokia
    Nokia is a Finnish multinational telecommunications and consumer electronics company best known for its historic leadership in mobile phones and its current focus on network infrastructure and 5G technologies.
  • E. BlackBerry smartphone
    The BlackBerry smartphone is a mobile device line best known for its physical QWERTY keyboard, secure email and messaging capabilities, and popularity among business and government users in the 2000s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb1bb90008190947ac0961393446d completed April 14, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94acd8288190a91bf09220126e13 completed May 8, 2026, 7:45 a.m.
Created at: April 10, 2026, 1:22 a.m.