Triple

T22649874
Position Surface form Disambiguated ID Type / Status
Subject Vercel E559063 entity
Predicate product P490 FINISHED
Object Vercel AI 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: Vercel AI SDK | Statement: [Vercel, product, Vercel AI SDK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vercel AI SDK
Context triple: [Vercel, product, Vercel AI SDK]
  • A. Vercel chosen
    Vercel is a cloud platform for frontend developers, best known for hosting and developing modern web applications and for creating the popular React framework Next.js.
  • B. OpenAI API platform
    The OpenAI API platform is a cloud-based service that provides developers with programmatic access to OpenAI’s language, code, and other AI models for integration into applications and workflows.
  • C. AI21 Labs
    AI21 Labs is an artificial intelligence company specializing in large language models and advanced natural language processing technologies.
  • D. OpenAI Codex API
    The OpenAI Codex API is a cloud-based interface that lets developers integrate Codex’s natural-language-to-code generation and code understanding capabilities into their own applications and tools.
  • E. Gradio
    Gradio is an open-source Python library that lets users quickly build and share interactive web interfaces for machine learning models and data science workflows.
  • 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_69e245489dd88190b1f674acf61c8769 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1703b40b88190aec5cf2fa28bfcbf completed April 29, 2026, 2:43 a.m.
Created at: April 17, 2026, 3:05 p.m.