Triple

T36704323
Position Surface form Disambiguated ID Type / Status
Subject Extensions of Recurrent Neural Network Language Model E906312 entity
Predicate hasCitationType P190718 FINISHED
Object computer science paper 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: computer science paper | Statement: [Extensions of Recurrent Neural Network Language Model, hasCitationType, computer science paper]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCitationType
Context triple: [Extensions of Recurrent Neural Network Language Model, hasCitationType, computer science paper]
  • A. hasCitationForm
    Indicates that an entity is associated with a specific standardized form used for citing or referencing it.
  • B. hasCitationSystem
    Indicates that one entity uses, follows, or is governed by a particular citation or referencing system defined by another entity.
  • C. hasCitationInformation
    Indicates that an entity is associated with specific citation details, such as source, reference, or bibliographic information.
  • D. hasCitationStatus
    Indicates the current citation-related state or condition assigned to a referenced work or source (e.g., cited, uncited, pending, or deprecated).
  • E. hasCitationRole
    Indicates that an entity participates in a citation with a specific role or function (such as being the citing work, cited work, or contextual reference).
  • 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_69f76e7195c48190b5580c9cfb01e95f completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fcce2cf9188190b3f65b362203a6a3 completed May 7, 2026, 5:38 p.m.
PD Predicate disambiguation batch_69fcccee6240819084680887731ff64b completed May 7, 2026, 5:33 p.m.
PDg Predicate description generation batch_69fccdd2d84481909a7ce22407def9c7 completed May 7, 2026, 5:37 p.m.
Created at: May 3, 2026, 4:12 p.m.