Triple

T364267
Position Surface form Disambiguated ID Type / Status
Subject Google Brain E7923 entity
Predicate partOf P40 FINISHED
Object Google AI E7923 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: Google AI | Statement: [Google Brain, partOf, Google AI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Google AI
Context triple: [Google Brain, partOf, Google AI]
  • A. Google Brain chosen
    Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
  • B. Meta AI
    Meta AI is Meta Platforms’ artificial intelligence division, responsible for developing large-scale AI models, research, and consumer-facing tools like the Meta AI assistant integrated across its apps and services.
  • C. DeepMind
    DeepMind is a leading artificial intelligence research company renowned for breakthroughs such as AlphaGo and deep reinforcement learning, operating as a subsidiary of Google.
  • D. OpenAI
    OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
  • E. Google
    Google is a multinational technology company best known for its search engine and wide range of internet-related products and services, including Android, YouTube, and cloud computing.
  • 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_69a2e7e880008190a6ad7e06e5d03007 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ebd1016481909b8ba3b047a47145 completed Feb. 28, 2026, 1:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3e86533a481909bab5f0b52114c6a completed March 1, 2026, 7:19 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.