Triple
T4279929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amazon DynamoDB |
E97122
|
entity |
| Predicate | globalFeature |
P5048
|
FINISHED |
| Object | multi-region replication via global tables |
—
|
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: multi-region replication via global tables | Statement: [Amazon DynamoDB, globalFeature, multi-region replication via global tables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: globalFeature Context triple: [Amazon DynamoDB, globalFeature, multi-region replication via global tables]
-
A.
keyFeature
Indicates that something is a primary, distinguishing, or most important feature of an entity.
-
B.
iconicFeature
Indicates that something serves as a distinctive, widely recognized characteristic or symbol of another entity.
-
C.
featureType
chosen
Indicates the specific kind or category of feature that characterizes or distinguishes an entity.
-
D.
typicalFeatures
Indicates that the related entities are characteristic or commonly occurring features or attributes of something.
-
E.
featuresSample
Indicates that an entity includes or presents a particular sample as one of its components or examples.
- 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350367da48190b735deef9b5d2d2e |
completed | March 12, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69b347fc4c0c8190a7fcd814e27308a5 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:07 p.m.