Triple

T11003643
Position Surface form Disambiguated ID Type / Status
Subject Neural Turing Machines E260059 entity
Predicate hasExternalMemory P96956 FINISHED
Object differentiable memory matrix 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: differentiable memory matrix | Statement: [Neural Turing Machines, hasExternalMemory, differentiable memory matrix]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasExternalMemory
Context triple: [Neural Turing Machines, hasExternalMemory, differentiable memory matrix]
  • A. hasMemoryIn
    Indicates that an entity possesses or stores memory, information, or experiences within a specified context, location, or medium.
  • B. hasStorage
    Indicates that one entity provides or contains storage capacity or space for another entity or resource.
  • C. hasRAM
    Indicates that an entity possesses or is equipped with a specified amount or type of random-access memory (RAM).
  • D. supportsExternalDrive
    Indicates that one entity is capable of working with, recognizing, or providing functionality for an external storage drive.
  • E. hasMemorySlot
    Indicates that an entity possesses a specific memory slot or storage location for holding information or data.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797553c408190b8dca21250243479 completed April 9, 2026, 12:11 p.m.
PD Predicate disambiguation batch_69d72e96be6c8190a46c69f61b2d8cd4 completed April 9, 2026, 4:44 a.m.
PDg Predicate description generation batch_69d733b27ffc81908ab1b8df198cd5c7 completed April 9, 2026, 5:05 a.m.
Created at: April 8, 2026, 9:25 p.m.