Triple

T14264891
Position Surface form Disambiguated ID Type / Status
Subject Gary Starkweather E353619 entity
Predicate employer P7 FINISHED
Object Microsoft E1649 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 | Statement: [Gary Starkweather, employer, Microsoft]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Microsoft
Context triple: [Gary Starkweather, employer, Microsoft]
  • A. Microsoft chosen
    Microsoft is a multinational technology company best known for its Windows operating system, Office productivity suite, and Azure cloud computing platform.
  • B. Micros Systems
    Micros Systems was a leading provider of point-of-sale and hospitality management software and hardware solutions for restaurants, hotels, and retail businesses.
  • C. WIN Corporation
    WIN Corporation is an Australian media company best known for owning and operating the WIN Television network and related broadcasting assets.
  • D. Microsoft Imagine
    Microsoft Imagine was an academic program by Microsoft that provided students and educators with free or discounted access to professional developer and design tools, later rebranded as Azure Dev Tools for Teaching.
  • E. Microsoft Auto
    Microsoft Auto is an embedded automotive software platform developed by Microsoft to power in-car infotainment and navigation systems.
  • 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_69d8278c43e08190824146f4632b89a5 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6357a8188190ba518a486521052b completed April 14, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326367348190b4b31b32f4ca5639 completed May 8, 2026, 12:46 a.m.
Created at: April 10, 2026, 1:09 a.m.