Triple

T36491657
Position Surface form Disambiguated ID Type / Status
Subject Prototypical Networks E899064 entity
Predicate inferenceStep P132547 FINISHED
Object compute prototype for each class from support set LITERAL 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: compute prototype for each class from support set | Statement: [Prototypical Networks, inferenceStep, compute prototype for each class from support set]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: inferenceStep
Context triple: [Prototypical Networks, inferenceStep, compute prototype for each class from support set]
  • A. inferenceAlgorithm
    Indicates that one entity is an algorithm or method used to draw conclusions or derive new information from data or premises about another entity.
  • B. stepOfModel chosen
    Indicates that something is a specific step or stage within a larger model or process.
  • C. stepping
    Indicates that an entity is moving its foot or feet to take a step, often as part of walking or changing position.
  • D. supportsInferenceOf
    Indicates that one entity provides a logical basis or justification for concluding or deriving another entity.
  • E. isStepToward
    Indicates that one action, state, or condition serves as progress or a necessary move in the direction of achieving another.
  • F. None of above.

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_69f76e5ad4588190bdbce60c52fbb785 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7be9d07ac8190adf796cbef60daf6 completed May 3, 2026, 9:31 p.m.
PD Predicate disambiguation batch_69f7bccf05bc8190b61fdb2b2a315811 completed May 3, 2026, 9:23 p.m.
Created at: May 3, 2026, 4:10 p.m.