Triple
T27762491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transformer-XL |
E701503
|
entity |
| Predicate | memoryMechanismType |
P9896
|
FINISHED |
| Object | segment-level recurrence over hidden states |
—
|
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: segment-level recurrence over hidden states | Statement: [Transformer-XL, memoryMechanismType, segment-level recurrence over hidden states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryMechanismType Context triple: [Transformer-XL, memoryMechanismType, segment-level recurrence over hidden states]
-
A.
memoryType
chosen
Indicates the specific category or kind of memory associated with an entity or process.
-
B.
memoryFunction
Indicates a relationship where an entity serves as or performs a memory-related function for another entity or system.
-
C.
memory
Indicates that an entity retains, recalls, or is associated with stored information or past experiences.
-
D.
storageMechanism
Indicates the method or system by which something is stored, preserved, or kept for later use.
-
E.
memoryState
Indicates the condition or configuration of an entity’s stored information at a particular point in time.
- 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_69f66c5c13808190887180099745673b |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f66abddc448190a488852f8abdeb2c |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 27, 2026, 4:28 p.m.