Triple
T7033344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FLAC |
E163320
|
entity |
| Predicate | typicalCompressionRatio |
P12420
|
FINISHED |
| Object | 30–60 percent size reduction |
—
|
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: 30–60 percent size reduction | Statement: [FLAC, typicalCompressionRatio, 30–60 percent size reduction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalCompressionRatio Context triple: [FLAC, typicalCompressionRatio, 30–60 percent size reduction]
-
A.
compressionRatio
chosen
Indicates the proportional reduction in size or volume achieved when something is compressed compared to its original size.
-
B.
compressionType
Indicates the method or format used to compress data or content in the relationship.
-
C.
compressorType
Indicates the specific kind or category of compressor associated with an entity.
-
D.
lensCompressionFactor
Indicates the degree to which a lens alters perceived depth and distance relationships in an image compared to real-world geometry.
-
E.
typicalLength
Indicates the usual or characteristic length associated with an entity or phenomenon.
- 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_69c6885d691c81908cf7d31083113886 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e458ad9c81908c3f492b317ce291 |
completed | March 27, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69c6e1b9a2488190aea351d96afa5a12 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:36 p.m.