Triple
T27734995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | System.IO.Compression.DeflateStream |
E697508
|
entity |
| Predicate | enumUsed |
P18110
|
FINISHED |
| Object |
System.IO.Compression.CompressionLevel
System.IO.Compression.CompressionLevel is a .NET enumeration that specifies the trade-off between compression speed and compression efficiency for compression streams and related APIs.
|
E1787491
|
NE FINISHED |
How this triple was built (3 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: System.IO.Compression.CompressionLevel | Statement: [System.IO.Compression.DeflateStream, enumUsed, System.IO.Compression.CompressionLevel]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: System.IO.Compression.CompressionLevel Triple: [System.IO.Compression.DeflateStream, enumUsed, System.IO.Compression.CompressionLevel]
Generated description
System.IO.Compression.CompressionLevel is a .NET enumeration that specifies the trade-off between compression speed and compression efficiency for compression streams and related APIs.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enumUsed Context triple: [System.IO.Compression.DeflateStream, enumUsed, System.IO.Compression.CompressionLevel]
-
A.
variantCount
Indicates the number of distinct variants associated with a given entity or item.
-
B.
indexUsedBy
Indicates that a particular index is utilized or referenced by another entity, such as a query, process, or data structure.
-
C.
hasNumberOfUses
Indicates the quantity of times something can be or is intended to be used.
-
D.
usedInType
chosen
Indicates that something serves as a component, element, or example within a particular type or category.
-
E.
usedOrdinal
Indicates that one entity is used as an ordinal indicator or position marker relative to another entity.
- F. None of above.
Provenance (6 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_69ef590c3e288190ad54d2465af8ca4e |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63894e5848190aec428392562ab06 |
completed | May 2, 2026, 5:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12e4732d888190a3680cbdc50398be |
completed | May 24, 2026, 11:43 a.m. |
| NEDg | Description generation | batch_6a12e4fd4b248190946024cf76a5bced |
completed | May 24, 2026, 11:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a12e64b90cc819091f51c6cf1ecb148 |
completed | May 24, 2026, 11:51 a.m. |
| PD | Predicate disambiguation | batch_69f6370c8c7c8190a02ea82847bb6e76 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 3:12 p.m.