Triple

T146311
Position Surface form Disambiguated ID Type / Status
Subject OpenAI E3337 entity
Predicate developed P73 FINISHED
Object GPT
GPT is a family of large language models created by OpenAI that can understand and generate human-like text for a wide range of tasks.
 E3337 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: GPT | Statement: [OpenAI, developed, GPT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GPT
Context triple: [OpenAI, developed, GPT]
  • A. DALL·E
    DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
  • B. ChatGPT Plus
    ChatGPT Plus is a paid subscription tier of OpenAI’s ChatGPT service that offers enhanced access, faster performance, and priority use of advanced models compared to the free version.
  • C. Claude
    Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
  • D. OpenAI
    OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
  • E. BARD Mobile app
    The BARD Mobile app is a specialized application that provides accessible audio and braille books and magazines to people who are blind, visually impaired, or print disabled.
  • 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: GPT
Triple: [OpenAI, developed, GPT]
Generated description
GPT is a family of large language models created by OpenAI that can understand and generate human-like text for a wide range of tasks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GPT
Target entity description: GPT is a family of large language models created by OpenAI that can understand and generate human-like text for a wide range of tasks.
  • A. DALL·E
    DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
  • B. ChatGPT Plus
    ChatGPT Plus is a paid subscription tier of OpenAI’s ChatGPT service that offers enhanced access, faster performance, and priority use of advanced models compared to the free version.
  • C. Claude
    Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
  • D. OpenAI chosen
    OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
  • E. BARD Mobile app
    The BARD Mobile app is a specialized application that provides accessible audio and braille books and magazines to people who are blind, visually impaired, or print disabled.
  • F. None of above.

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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a257ea7eac8190884a53453a9e0dd6 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2c52df3b48190960c53fd872ff897 completed Feb. 28, 2026, 10:36 a.m.
NEDg Description generation batch_69a2c5a7925481909fa398453451a126 completed Feb. 28, 2026, 10:38 a.m.
NED2 Entity disambiguation (via description) batch_69a2c60ae5108190b735939eac69e11a completed Feb. 28, 2026, 10:40 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.