Triple
T7936032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EISA |
E184290
|
entity |
| Predicate | supports |
P516
|
FINISHED |
| Object | DMA |
E38930
|
NE 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: DMA | Statement: [EISA, supports, DMA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DMA Context triple: [EISA, supports, DMA]
-
A.
DMA
chosen
DMA (Direct Memory Access) is a computer feature that allows hardware devices to transfer data directly to and from system memory without continuous CPU involvement, improving performance and efficiency.
-
B.
DMA
DMA is the IATA airport code for Davis-Monthan Air Force Base, a major U.S. Air Force installation near Tucson, Arizona.
-
C.
DDR
DDR is the commonly used German abbreviation for the former socialist state officially known as the German Democratic Republic (East Germany), which existed from 1949 to 1990.
-
D.
DRAM
DRAM is an American rapper and singer known for his eclectic blend of hip hop, R&B, and soul, highlighted by his hit single "Broccoli."
-
E.
DRAM
DRAM (Dynamic Random-Access Memory) is a type of volatile semiconductor memory widely used as the main system memory in computers and other digital devices due to its high density and relatively low cost.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8290c21c8190906a5ca6fe2b03c4 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3aede3cc81908b0d3b54e68997b9 |
completed | March 31, 2026, 3:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5c0791e48190af18299c22f6a804 |
completed | March 31, 2026, 5:30 a.m. |
Created at: March 30, 2026, 5:08 p.m.