Triple

T900538
Position Surface form Disambiguated ID Type / Status
Subject GPT-4 E19435 entity
Predicate modelFamily P11218 FINISHED
Object GPT series
The GPT series is a family of large language models developed by OpenAI that generate human-like text and perform a wide range of natural language tasks.
E106918 NE FINISHED

How this triple was built (5 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 series | Statement: [GPT-4, modelFamily, GPT series]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GPT series
Context triple: [GPT-4, modelFamily, GPT series]
  • A. GPT-3
    GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
  • B. GPT-4
    GPT-4 is a large multimodal language model known for its advanced reasoning, comprehension, and generation capabilities across text and images.
  • C. ChatGPT
    ChatGPT is an advanced conversational AI model developed by OpenAI that can understand and generate human-like text across a wide range of topics and tasks.
  • D. GPT-2
    GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
  • E. GPT-3.5
    GPT-3.5 is a large language model that generates human-like text and powers conversational AI applications such as advanced chatbots and coding assistants.
  • 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 series
Triple: [GPT-4, modelFamily, GPT series]
Generated description
The GPT series is a family of large language models developed by OpenAI that generate human-like text and perform a wide range of natural language tasks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: GPT series
Target entity description: The GPT series is a family of large language models developed by OpenAI that generate human-like text and perform a wide range of natural language tasks.
  • A. GPT-3
    GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
  • B. GPT-4
    GPT-4 is a large multimodal language model known for its advanced reasoning, comprehension, and generation capabilities across text and images.
  • C. ChatGPT
    ChatGPT is an advanced conversational AI model developed by OpenAI that can understand and generate human-like text across a wide range of topics and tasks.
  • D. GPT-2
    GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
  • E. GPT-3.5
    GPT-3.5 is a large language model that generates human-like text and powers conversational AI applications such as advanced chatbots and coding assistants.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: modelFamily
Context triple: [GPT-4, modelFamily, GPT series]
  • A. productFamily chosen
    Indicates that one product belongs to, or is categorized under, a broader product family or line.
  • B. model
    Indicates that one entity serves as a representation, example, or simulation of another entity or concept.
  • C. introducedModelFamily
    Indicates that an entity (such as a person or organization) is responsible for first presenting or launching a particular model family.
  • D. typeFamily
    Indicates that one entity is classified as a family-related type or belongs to a family category in relation to another entity.
  • E. designFamily
    Indicates a relationship where one entity belongs to, or is categorized within, a particular design family or style group defined by another entity.
  • F. None of above.

Provenance (6 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad42ecac81909f8bc554d2fe0363 completed March 1, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c734e680819098840e9c736b5ead completed March 4, 2026, 5:46 a.m.
NEDg Description generation batch_69a7c8a3064081908772ee2305bbe3e1 completed March 4, 2026, 5:52 a.m.
NED2 Entity disambiguation (via description) batch_69a7c8fecaac8190a7b1a1cd2fa98a2d completed March 4, 2026, 5:54 a.m.
PD Predicate disambiguation batch_69a4aa979d408190b17ccfde132ea628 completed March 1, 2026, 9:07 p.m.
Created at: March 1, 2026, 7:39 p.m.