Triple

T32215708
Position Surface form Disambiguated ID Type / Status
Subject Computational Learning Theory E822917 entity
Predicate hasKeyModel P14613 FINISHED
Object PAC model
The PAC (Probably Approximately Correct) model is a foundational framework in computational learning theory that formalizes what it means for an algorithm to efficiently learn a function from examples with high accuracy and confidence.
 E1997108 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: PAC model | Statement: [Computational Learning Theory, hasKeyModel, PAC model]
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: PAC model
Triple: [Computational Learning Theory, hasKeyModel, PAC model]
Generated description
The PAC (Probably Approximately Correct) model is a foundational framework in computational learning theory that formalizes what it means for an algorithm to efficiently learn a function from examples with high accuracy and confidence.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasKeyModel
Context triple: [Computational Learning Theory, hasKeyModel, PAC model]
  • A. hasKeyStructure
    Indicates that one entity possesses or defines the primary structural framework or core structural pattern of another entity.
  • B. hasKeyRelationship
    Indicates a relationship where one entity serves as a key (e.g., identifier, access token, or primary reference) that grants access to, controls, or uniquely identifies another entity.
  • C. hasKeyInformation
    Indicates that an entity possesses or contains essential or critical information relevant to another entity, context, or task.
  • D. hasKeyElement chosen
    Indicates that one entity contains or depends on another entity that serves as a primary or essential component.
  • E. hasKeySupporter
    Indicates that an entity has a primary or crucial supporter who significantly backs or advocates for it.
  • 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_69f3490a3bec819097bc58d4731b9d08 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f7979a073881909a4fde2558e6b6f3 completed May 3, 2026, 6:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2f3b9e07148190b1c0485c4d8dca9c completed June 14, 2026, 11:39 p.m.
NEDg Description generation batch_6a2f3c207d988190835c5bda034bbc6c completed June 14, 2026, 11:41 p.m.
NED2 Entity disambiguation (via description) batch_6a2f3ef33fc08190bdedc81c93429535 completed June 14, 2026, 11:53 p.m.
PD Predicate disambiguation batch_69f7961550f88190b7bb8a9155458b54 completed May 3, 2026, 6:38 p.m.
Created at: May 1, 2026, 12:37 a.m.