Triple
T36490351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reformer: The Efficient Transformer |
E899034
|
entity |
| Predicate | LSHAttentionProperty |
P79475
|
FINISHED |
| Object | groups similar queries into buckets |
—
|
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: groups similar queries into buckets | Statement: [Reformer: The Efficient Transformer, LSHAttentionProperty, groups similar queries into buckets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: LSHAttentionProperty Context triple: [Reformer: The Efficient Transformer, LSHAttentionProperty, groups similar queries into buckets]
-
A.
usesSelfAttention
Indicates that an entity employs a self-attention mechanism to compute representations by relating each part of its input to all other parts.
-
B.
numberOfAttentionHeads
Indicates the number of distinct attention heads used within an attention mechanism or layer in a model.
-
C.
algorithmicProperty
chosen
Indicates that a subject possesses a specific characteristic, behavior, or quality defined in terms of an algorithm or computational procedure.
-
D.
embeddingType
Indicates the specific kind or category of embedding representation used to encode an entity or data.
-
E.
usesLSA
Indicates that one entity employs Latent Semantic Analysis (LSA) as a method, tool, or underlying technique in relation to another entity or data.
- 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.