Triple
T27762492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transformer-XL |
E701503
|
entity |
| Predicate | positionalEncodingType |
P28140
|
FINISHED |
| Object | relative positional encoding |
—
|
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: relative positional encoding | Statement: [Transformer-XL, positionalEncodingType, relative positional encoding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionalEncodingType Context triple: [Transformer-XL, positionalEncodingType, relative positional encoding]
-
A.
embeddingType
Indicates the specific kind or category of embedding representation used to encode an entity or data.
-
B.
pretrainingType
Indicates the specific kind or category of pretraining process that has been applied to an entity (such as a model or system).
-
C.
offsetType
Indicates the specific kind or category of offset applied in a relationship, such as how far or in what manner one value, position, or event is shifted relative to another.
-
D.
encodedIn
Indicates that one entity is represented, stored, or expressed within another entity using a specific encoding or format.
-
E.
encodingStructure
chosen
Indicates the structural scheme or format used to encode information 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_69ef6a5193808190816eb7d0020b2d87 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c475c58c8190a883554231e88c88 |
completed | May 3, 2026, 9:56 p.m. |
Created at: April 27, 2026, 4:28 p.m.