Triple
T22109497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HSPA+ |
E546376
|
entity |
| Predicate | downlinkPeakRate |
P45736
|
FINISHED |
| Object | 21 Mbit/s |
—
|
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: 21 Mbit/s | Statement: [HSPA+, downlinkPeakRate, 21 Mbit/s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: downlinkPeakRate Context triple: [HSPA+, downlinkPeakRate, 21 Mbit/s]
-
A.
downlinkMethod
Indicates the method or technology used to transmit data from a remote system (e.g., satellite or spacecraft) down to a receiving station.
-
B.
bandwidthCharacteristic
Indicates the relationship specifying the bandwidth-related properties or constraints associated with a connection, link, or communication channel.
-
C.
dataRate
Indicates the rate at which data is transmitted, processed, or transferred between entities over a given time interval.
-
D.
hasMaximumBandwidth
Indicates the maximum data transfer capacity that can be allocated, supported, or utilized in a given connection or system.
-
E.
maximumBitrate
chosen
Indicates the highest data transfer rate allowed or supported for a given media stream or connection.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291b9c988190b3ddd06d1f40dc78 |
completed | April 28, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69e71b2ed7348190b6fa2e52f54393fb |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:30 p.m.