Triple
T18724009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Attention Is All You Need |
E457850
|
entity |
| Predicate | replacedArchitecture |
P10258
|
FINISHED |
| Object | recurrent neural networks |
—
|
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: recurrent neural networks | Statement: [Attention Is All You Need, replacedArchitecture, recurrent neural networks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedArchitecture Context triple: [Attention Is All You Need, replacedArchitecture, recurrent neural networks]
-
A.
replacedStructure
chosen
Indicates that one structure has been substituted for, or taken the place of, another structure.
-
B.
replacedSubsystem
Indicates that one subsystem has been substituted or exchanged for another, taking over its role or function.
-
C.
replacedPlatform
Indicates that one platform has been superseded or taken over by another platform.
-
D.
replacedEarlierSystems
Indicates that one system has taken the place of and superseded other systems that existed or were in use before it.
-
E.
replacedStructureType
Indicates that one structure type has been substituted or superseded by another structure type.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56abcfc048190a01dee959e768768 |
completed | April 19, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:50 a.m.