Triple

T5451860
Position Surface form Disambiguated ID Type / Status
Subject Files E122387 entity
Predicate supportsService P203 FINISHED
Object Microsoft OneDrive E5700 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: Microsoft OneDrive | Statement: [Files, supportsService, Microsoft OneDrive]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Microsoft OneDrive
Context triple: [Files, supportsService, Microsoft OneDrive]
  • A. OneDrive chosen
    OneDrive is Microsoft’s cloud storage and file synchronization service that lets users securely store, access, and share files across devices and online.
  • B. Dropbox
    Dropbox is a cloud-based file storage and collaboration company known for enabling users to easily sync and share files across devices.
  • C. Dropbox
    Dropbox is an American hard rock band known for their melodic yet heavy sound and for their connections to the post-grunge and alternative metal scenes of the early 2000s.
  • D. Google Drive
    Google Drive is a cloud-based file storage and synchronization service by Google that lets users store, share, and access files from any internet-connected device.
  • E. Zoho WorkDrive
    Zoho WorkDrive is a cloud-based file storage, collaboration, and team content management platform offered by Zoho.
  • 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_69bd46424248819085282ddf50a565f3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91dfec248190af6f9c793a99c34c completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf413d25008190b100c8297d6063b1 completed March 22, 2026, 1:09 a.m.
Created at: March 20, 2026, 2:08 p.m.