Triple

T871358
Position Surface form Disambiguated ID Type / Status
Subject GPT-3 E18819 entity
Predicate describedInPaper P519 FINISHED
Object Language Models are Few-Shot Learners E18819 NE FINISHED

How this triple was built (3 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: Language Models are Few-Shot Learners | Statement: [GPT-3, describedInPaper, Language Models are Few-Shot Learners]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Language Models are Few-Shot Learners
Context triple: [GPT-3, describedInPaper, Language Models are Few-Shot Learners]
  • A. GPT-3 chosen
    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. Hugging Face Transformers
    Hugging Face Transformers is a widely used open-source library that provides state-of-the-art transformer-based models and tools for natural language processing and related machine learning tasks.
  • C. 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.
  • D. CLIP
    CLIP is an OpenAI model that learns joint representations of images and text, enabling tasks like zero-shot image classification and natural language-based image retrieval.
  • 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.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: describedInPaper
Context triple: [GPT-3, describedInPaper, Language Models are Few-Shot Learners]
  • A. describedIn chosen
    Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
  • B. describes
    Indicates that one entity provides an explanation, representation, or account of another entity or concept.
  • C. presentedIn
    Indicates that something is shown, displayed, or formally introduced within a particular context, medium, event, or setting.
  • D. hasDescription
    Indicates that an entity is associated with a textual description that explains or characterizes it.
  • E. usedInManuscripts
    Indicates that something (such as a term, symbol, or feature) appears or is employed within one or more manuscripts.
  • F. None of above.

Provenance (4 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_69a4938db1f081909bcd1ad2713b6096 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac96850881908a2d776685126137 completed March 1, 2026, 9:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3cb9a648190981182add42325f3 completed March 4, 2026, 3:15 a.m.
PD Predicate disambiguation batch_69a4aa89ca008190b50d061ac7fe19f9 completed March 1, 2026, 9:07 p.m.
Created at: March 1, 2026, 7:39 p.m.