Triple
T36490248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reformer architecture |
E899032
|
entity |
| Predicate | reducesComplexityOf |
P9925
|
FINISHED |
| Object | self-attention |
—
|
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: self-attention | Statement: [Reformer architecture, reducesComplexityOf, self-attention]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reducesComplexityOf Context triple: [Reformer architecture, reducesComplexityOf, self-attention]
-
A.
controlsComplexityBy
Indicates that one entity manages, limits, or regulates the complexity of another entity, process, or system.
-
B.
reduces
chosen
Indicates that one entity causes a decrease in the amount, intensity, degree, or impact of another entity.
-
C.
simplified
Indicates that something has been made less complex or easier to understand, use, or represent compared to its original form.
-
D.
hasComplexity
Indicates that something possesses a certain level or type of complexity, often in terms of structure, behavior, or difficulty.
-
E.
designSimplification
Indicates a relationship where one entity reduces the complexity of another entity’s design, making it simpler or more streamlined.
- 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_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.