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.