Triple
T2066388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3D NAND |
E45909
|
entity |
| Predicate | storesDataAs |
P15687
|
FINISHED |
| Object | charge levels in floating gate or charge-trap structures |
—
|
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: charge levels in floating gate or charge-trap structures | Statement: [3D NAND, storesDataAs, charge levels in floating gate or charge-trap structures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: storesDataAs Context triple: [3D NAND, storesDataAs, charge levels in floating gate or charge-trap structures]
-
A.
storesDataType
chosen
Indicates that an entity is designed to hold, manage, or persist information of a specified data type.
-
B.
dataStorage
Indicates a relationship where one entity serves as a repository that holds, retains, or maintains data for another entity or process.
-
C.
storesObjectsAs
Indicates that one entity keeps or maintains other entities within it as stored items or contents.
-
D.
storesEnergyAs
Indicates that one entity retains or accumulates energy in the form or medium specified by another entity.
-
E.
storageOption
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
- 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_69a8891b38288190abd572ccad9b6928 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9f236f08190b602d337afb1880f |
completed | March 7, 2026, 5:38 a.m. |
| PD | Predicate disambiguation | batch_69abb7aee9b48190999620176e3a6ee2 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:40 p.m.