Triple
T22488385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tor Metrics |
E555949
|
entity |
| Predicate | dataSource |
P409
|
FINISHED |
| Object | Tor bridges |
—
|
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: Tor bridges | Statement: [Tor Metrics, dataSource, Tor bridges]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tor bridges Context triple: [Tor Metrics, dataSource, Tor bridges]
-
A.
Tor bridges
chosen
Tor bridges are alternative, often unlisted entry nodes to the Tor network designed to help users circumvent censorship and blocking of standard Tor relays.
-
B.
Tor
Tor is a masculine given name of Norse origin, commonly used in Scandinavian countries and derived from the name of the Norse thunder god Thor.
-
C.
Orbot
Orbot is a privacy-focused Android app that routes internet traffic through the Tor network to help users browse anonymously and circumvent censorship.
-
D.
Tor directory protocol
The Tor directory protocol is the system Tor uses to distribute and update network consensus and relay descriptors, enabling clients to discover and connect to Tor relays securely and reliably.
-
E.
Pluggable transports
Pluggable transports are modular protocols used by Tor to disguise and obfuscate network traffic, helping users circumvent censorship and traffic analysis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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. |
Created at: April 16, 2026, 8:49 p.m.