Triple

T19771992
Position Surface form Disambiguated ID Type / Status
Subject Cascade-Correlation learning architecture E474908 entity
Predicate hiddenUnitConnectionPattern P137270 FINISHED
Object new hidden units connect to all existing network units 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: new hidden units connect to all existing network units | Statement: [Cascade-Correlation learning architecture, hiddenUnitConnectionPattern, new hidden units connect to all existing network units]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hiddenUnitConnectionPattern
Context triple: [Cascade-Correlation learning architecture, hiddenUnitConnectionPattern, new hidden units connect to all existing network units]
  • A. hiddenSize
    Indicates the size or dimensionality of the internal representation used within a model or component that is not directly exposed as output.
  • B. usesFullyConnectedLayersAtEnd
    Indicates that the model’s architecture concludes with one or more fully connected (dense) layers applied after preceding layers or modules.
  • C. hasNeuralNetwork
    Indicates that an entity possesses, incorporates, or is equipped with a neural network.
  • D. hasNetworkStructure
    Indicates that one entity possesses, exhibits, or is organized according to a particular network-based structure defined by another entity or specification.
  • E. transmissionPattern
    Indicates how something is passed or spread from one entity to another, such as the mode or route of transmission.
  • F. None of above. chosen

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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6535ce4d08190a1dfca2df95a8631 completed April 20, 2026, 4:25 p.m.
PD Predicate disambiguation batch_69e53053ed2881908400becdfada7fd3 completed April 19, 2026, 7:43 p.m.
PDg Predicate description generation batch_69e532bbedf081908d801600e2af94a7 completed April 19, 2026, 7:53 p.m.
Created at: April 10, 2026, 1:48 p.m.