Triple

T19749805
Position Surface form Disambiguated ID Type / Status
Subject Object Storage Service E474346 entity
Predicate accessModel P58 FINISHED
Object SDK 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: SDK | Statement: [Object Storage Service, accessModel, SDK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SDK
Context triple: [Object Storage Service, accessModel, SDK]
  • A. SDK
    SDK is the three-letter IATA airport code assigned to Sandakan Airport in Sabah, Malaysia.
  • B. SDKs chosen
    SDKs (Software Development Kits) are collections of tools, libraries, documentation, and code samples that enable developers to build applications and integrate with specific platforms or services.
  • C. API
    The Anton Pannekoek Institute for Astronomy (API) is a research institute at the University of Amsterdam dedicated to astronomical and astrophysical research and education.
  • D. SDKÚ
    SDKÚ is a centre-right political party in Slovakia known for its liberal-conservative and pro-European orientation.
  • E. Desktop SDKs
    Desktop SDKs are software development kits that allow developers to embed Zoom’s video, audio, and collaboration capabilities directly into native desktop applications.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529875688190952af476aa5be492 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:47 p.m.