Triple

T17674743
Position Surface form Disambiguated ID Type / Status
Subject Spec# E440617 entity
Predicate developedBy P73 FINISHED
Object Microsoft Research E500290 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 Research | Statement: [Spec#, developedBy, Microsoft Research]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Microsoft Research
Context triple: [Spec#, developedBy, Microsoft Research]
  • A. Microsoft Research chosen
    Microsoft Research is the research division of Microsoft, dedicated to advancing computer science and related fields through fundamental and applied research.
  • B. Microsoft Research Cambridge
    Microsoft Research Cambridge is a leading European research laboratory of Microsoft focused on advancing computer science and related fields through fundamental and applied research.
  • C. Microsoft Research Asia
    Microsoft Research Asia is a leading research division of Microsoft based in the Asia-Pacific region, known for its influential work in computer science and artificial intelligence.
  • D. Adobe Research
    Adobe Research is the research arm of Adobe that advances cutting-edge technologies in areas such as computer graphics, computer vision, machine learning, and digital media.
  • E. Intel Labs
    Intel Labs is the research and innovation arm of Intel, focused on advancing cutting-edge technologies in areas such as computing, artificial intelligence, and semiconductor design.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46f6ba22081909e2099490c047378 completed April 19, 2026, 6 a.m.
NED1 Entity disambiguation (via context triple) batch_6a022323e2c08190b8a86b865a14dbbe completed May 11, 2026, 6:42 p.m.
Created at: April 10, 2026, 10 a.m.