Triple

T36490457
Position Surface form Disambiguated ID Type / Status
Subject Fast Decoding in Sequence Models Using Discrete Latent Variables E899037 entity
Predicate typeOfDecoding P14388 FINISHED
Object non-strictly-autoregressive decoding 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: non-strictly-autoregressive decoding | Statement: [Fast Decoding in Sequence Models Using Discrete Latent Variables, typeOfDecoding, non-strictly-autoregressive decoding]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typeOfDecoding
Context triple: [Fast Decoding in Sequence Models Using Discrete Latent Variables, typeOfDecoding, non-strictly-autoregressive decoding]
  • A. decodingMethod chosen
    Indicates the technique or process used to convert encoded or encrypted data back into its original, interpretable form.
  • B. decoderType
    Indicates the specific kind or category of decoder associated with or used by an entity.
  • C. decodingAbstraction
    Indicates the process or relationship by which a concrete encoded form is interpreted into a more general, conceptual, or higher-level representation.
  • D. typeOfDecoupling
    Indicates the specific manner or mechanism by which two previously connected or interdependent entities are separated or made independent from each other.
  • E. decompositionType
    Indicates the specific way in which a whole is broken down into its constituent parts or components.
  • 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_6a030e31e01881909c6032532cd3c31a completed May 12, 2026, 11:25 a.m.
PD Predicate disambiguation batch_6a030dadea008190abe0a5652784bdd6 completed May 12, 2026, 11:23 a.m.
Created at: May 3, 2026, 4:10 p.m.