Triple
T22488240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snowflake |
E555946
|
entity |
| Predicate | obfuscates |
P22860
|
FINISHED |
| Object | network paths between user and Tor network |
—
|
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: network paths between user and Tor network | Statement: [Snowflake, obfuscates, network paths between user and Tor network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: obfuscates Context triple: [Snowflake, obfuscates, network paths between user and Tor network]
-
A.
encodes
Indicates that one entity contains or represents the information, instructions, or structure of another in a coded or symbolic form.
-
B.
obscuredIn
chosen
Indicates that one entity is hidden, blocked, or made less visible due to the presence or influence of another entity.
-
C.
usesScrambling
Indicates that one entity applies a scrambling process or technique to another entity or to information associated with it.
-
D.
distorts
Indicates that one entity alters another in a way that changes, warps, or misrepresents its original form, appearance, or meaning.
-
E.
disguisedAs
Indicates that one entity is intentionally presenting itself as, or made to appear as, another entity in order to conceal its true identity.
- 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c3e73108190be5ca89ea96a85e4 |
completed | April 29, 2026, 1:17 a.m. |
| PD | Predicate disambiguation | batch_69e898b6eee08190ba673a0ee329e671 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:49 p.m.