Triple
T36491888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neural Turing Machines |
E899070
|
entity |
| Predicate | hasMemoryAccessMechanism |
P8166
|
FINISHED |
| Object | soft attention over memory locations |
—
|
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: soft attention over memory locations | Statement: [Neural Turing Machines, hasMemoryAccessMechanism, soft attention over memory locations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMemoryAccessMechanism Context triple: [Neural Turing Machines, hasMemoryAccessMechanism, soft attention over memory locations]
-
A.
hasMemoryIn
Indicates that an entity possesses or stores memory, information, or experiences within a specified context, location, or medium.
-
B.
hasMemorySlot
Indicates that an entity possesses a specific memory slot or storage location for holding information or data.
-
C.
hasMemoryStatus
Indicates the current state or condition of an entity’s memory (such as availability, usage, or health).
-
D.
hasMechanism
chosen
Indicates that one entity operates, functions, or produces an effect through the specified mechanism or process.
-
E.
supportsMemoryProtection
Indicates that one entity provides mechanisms to prevent unauthorized access or interference with another entity’s memory space.
- 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_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:10 p.m.