Triple

T29108385
Position Surface form Disambiguated ID Type / Status
Subject Differentiable Neural Computers E736824 entity
Predicate writeOperation P12126 FINISHED
Object erase and add vectors 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: erase and add vectors | Statement: [Differentiable Neural Computers, writeOperation, erase and add vectors]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: writeOperation
Context triple: [Differentiable Neural Computers, writeOperation, erase and add vectors]
  • A. writingOutput
    Indicates that one entity produces or generates written content as an output, typically as the result of a writing or text-creation process.
  • B. writesSystem
    Indicates that an entity authors or produces a system, such as designing, coding, or otherwise creating it.
  • C. writeStrategy
    Indicates that one entity develops or composes a plan or method for achieving a particular goal or outcome for another entity or context.
  • D. inOperation
    Indicates that an entity (such as a system, device, or facility) is currently active, functioning, and performing its intended operation.
  • E. operationOf chosen
    Indicates that one entity is the function, activity, or process carried out by another entity (such as a system, device, or organization).
  • 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_69f077ec765c81909474c88bcc8bab43 completed April 28, 2026, 9:03 a.m.
NER Named-entity recognition batch_69f661bc4db08190bd91745a1ebfc2ae completed May 2, 2026, 8:42 p.m.
PD Predicate disambiguation batch_69f65c2376a08190be5215171e908e69 completed May 2, 2026, 8:18 p.m.
Created at: April 28, 2026, 11:17 a.m.