Triple
T3727844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DVB-S |
E78991
|
entity |
| Predicate | forwardErrorCorrection |
P22596
|
FINISHED |
| Object | concatenated Reed-Solomon and convolutional coding |
—
|
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: concatenated Reed-Solomon and convolutional coding | Statement: [DVB-S, forwardErrorCorrection, concatenated Reed-Solomon and convolutional coding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forwardErrorCorrection Context triple: [DVB-S, forwardErrorCorrection, concatenated Reed-Solomon and convolutional coding]
-
A.
usesForwardErrorCorrection
chosen
Indicates that one entity applies forward error correction techniques to detect and correct errors in data transmitted to or received from another entity.
-
B.
errorRecovery
Indicates that an entity detects a failure or error condition and initiates actions to restore normal or acceptable operation.
-
C.
trackingErrorCharacteristic
Indicates the specific type or nature of the discrepancy between a tracked value and its reference or target over time.
-
D.
checksum
Indicates that a value has been computed from data to verify its integrity or detect errors in transmission or storage.
-
E.
requiresCorrection
Indicates that something is identified as needing modification, adjustment, or fixing to correct an error or deficiency.
- 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_69ad8b0e4650819090ad7cef094285e8 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcaf921bc81908bb347d6b9204670 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc0452f5081909c79e114a86cce8c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.