Triple
T28329985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LevelDB |
E717513
|
entity |
| Predicate | defaultCompression |
P27672
|
FINISHED |
| Object | Snappy |
—
|
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: Snappy | Statement: [LevelDB, defaultCompression, Snappy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defaultCompression Context triple: [LevelDB, defaultCompression, Snappy]
-
A.
defaultCompressionLevel
Indicates the standard or preconfigured degree of compression applied when no specific compression level is explicitly set.
-
B.
compressionType
chosen
Indicates the method or format used to compress data or content in the relationship.
-
C.
compressionStandard
Indicates that one entity uses, supports, or is defined according to a particular data compression standard specified by the other entity.
-
D.
compressionMode
Indicates the specific method or setting used to compress data or content in a given context.
-
E.
compressionFunctionType
Indicates the specific kind or category of compression function applied in a compression process or algorithm.
- 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6db1f3ec48190a82e7d893d3c76ba |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
Created at: April 28, 2026, 12:31 a.m.