Triple
T37657784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SQL Server login |
E937643
|
entity |
| Predicate | hasMetadataIn |
P5500
|
FINISHED |
| Object | sys.sql_logins catalog view |
—
|
NE NERFINISHED |
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: sys.sql_logins catalog view | Statement: [SQL Server login, hasMetadataIn, sys.sql_logins catalog view]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMetadataIn Context triple: [SQL Server login, hasMetadataIn, sys.sql_logins catalog view]
-
A.
hasMetadata
chosen
Indicates that one entity is associated with descriptive or informational data about another entity.
-
B.
hasMetaSubject
Indicates that an entity is associated with a subject at a meta-level, such as the topic, theme, or aboutness of the entity rather than its direct content or participants.
-
C.
hasLanguageMetadata
Indicates that an entity is associated with descriptive information about the language(s) it uses or is expressed in.
-
D.
hasMetapattern
Indicates that one entity is associated with, characterized by, or governed by a higher-level structural pattern or schema represented by another entity.
-
E.
hasMetaLevel
Indicates that one entity operates at a higher, more abstract, or descriptive level relative to another entity (e.g., data about data, rules about rules, or models about models).
- 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ffa15d53208190ab8574d6c7913e18 |
completed | May 9, 2026, 9:04 p.m. |
| PD | Predicate disambiguation | batch_69ff9eee681c81909434e79c627cb528 |
completed | May 9, 2026, 8:54 p.m. |
Created at: May 3, 2026, 4:18 p.m.