Triple

T9298150
Position Surface form Disambiguated ID Type / Status
Subject Tensor Cores E223691 entity
Predicate exposedThrough P87910 FINISHED
Object WMMA API
The WMMA API is NVIDIA’s programming interface that lets developers perform warp-level matrix multiply-accumulate operations to efficiently leverage Tensor Cores for mixed-precision linear algebra.
 E790552 NE FINISHED

How this triple was built (4 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: WMMA API | Statement: [Tensor Cores, exposedThrough, WMMA API]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WMMA API
Context triple: [Tensor Cores, exposedThrough, WMMA API]
  • A. MMArena
    MMArena is a modern football stadium in Le Mans, France, primarily used for hosting Le Mans FC’s home matches and other sporting events.
  • B. WWA
    WWA is the National Rail station code for Woolwich Arsenal railway station in southeast London.
  • C. WSM
    WSM is the three-letter ISO 3166-1 alpha-3 country code assigned to Samoa.
  • D. WWC
    WWC is a U.S. Department of Education initiative that reviews and summarizes research evidence on educational programs, practices, and policies to inform educators and policymakers.
  • E. WMN
    WMN is the National Rail station code for Warminster railway station in Wiltshire, England.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: WMMA API
Triple: [Tensor Cores, exposedThrough, WMMA API]
Generated description
The WMMA API is NVIDIA’s programming interface that lets developers perform warp-level matrix multiply-accumulate operations to efficiently leverage Tensor Cores for mixed-precision linear algebra.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WMMA API
Target entity description: The WMMA API is NVIDIA’s programming interface that lets developers perform warp-level matrix multiply-accumulate operations to efficiently leverage Tensor Cores for mixed-precision linear algebra.
  • A. MMArena
    MMArena is a modern football stadium in Le Mans, France, primarily used for hosting Le Mans FC’s home matches and other sporting events.
  • B. WWA
    WWA is the National Rail station code for Woolwich Arsenal railway station in southeast London.
  • C. WSM
    WSM is the three-letter ISO 3166-1 alpha-3 country code assigned to Samoa.
  • D. WWC
    WWC is a U.S. Department of Education initiative that reviews and summarizes research evidence on educational programs, practices, and policies to inform educators and policymakers.
  • E. WMN
    WMN is the National Rail station code for Warminster railway station in Wiltshire, England.
  • F. None of above. chosen

Provenance (5 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_69ca8423edb08190bc0c91287a484768 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd089e3ae88190aa4181cdd85a67b8 completed April 1, 2026, 11:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b251c4148190a94fafdc23a601d6 completed April 4, 2026, 6:40 a.m.
NEDg Description generation batch_69d0b65ea4548190b445563ac695b008 completed April 4, 2026, 6:57 a.m.
NED2 Entity disambiguation (via description) batch_69d0b6f504a48190878db828312e8a97 completed April 4, 2026, 7 a.m.
Created at: March 30, 2026, 7:36 p.m.