Triple
T2556443
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Azure SQL Managed Instance |
E56739
|
entity |
| Predicate | compatibilityLevel |
P40831
|
FINISHED |
| Object | near 100% compatibility with SQL Server |
—
|
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: near 100% compatibility with SQL Server | Statement: [Azure SQL Managed Instance, compatibilityLevel, near 100% compatibility with SQL Server]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compatibilityLevel Context triple: [Azure SQL Managed Instance, compatibilityLevel, near 100% compatibility with SQL Server]
-
A.
compatibilityGoal
Indicates that one entity has an objective or intended outcome related to being compatible or achieving compatibility with another entity.
-
B.
requiresCompatibilityWith
Indicates that one entity can only function correctly or be used if it is compatible with another specified entity.
-
C.
requiresLanguageVersion
Indicates that one entity depends on or must use a specific version of a language in order to function or be considered valid.
-
D.
backwardCompatibility
Indicates that one entity remains functional or compatible when used with an earlier version or older form of another entity.
-
E.
backwardCompatibleWith
Indicates that one entity can correctly interpret, use, or function with data, interfaces, or behavior designed for an earlier version of another entity.
- F. None of above. chosen
Provenance (4 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_69ab4a4bfec081908039988ec4c86e28 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd5a33234819082ad49fa6594b6be |
completed | March 7, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69abd0c8b6f08190a68645db3e8b779a |
completed | March 7, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69abd5a1cd508190a660b9a3c6b7cbcb |
completed | March 7, 2026, 7:37 a.m. |
Created at: March 6, 2026, 9:48 p.m.