Triple
T3453072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DVB-T2 |
E72835
|
entity |
| Predicate | backwardsCompatibleWithDVB-T |
P4635
|
FINISHED |
| Object | no |
—
|
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: no | Statement: [DVB-T2, backwardsCompatibleWithDVB-T, no]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backwardsCompatibleWithDVB-T Context triple: [DVB-T2, backwardsCompatibleWithDVB-T, no]
-
A.
backwardCompatibleWith
chosen
Indicates that one entity can correctly interpret, use, or function with data, interfaces, or behavior designed for an earlier version of another entity.
-
B.
backwardCompatibility
Indicates that one entity remains functional or compatible when used with an earlier version or older form of another entity.
-
C.
compatibleStand
Indicates that one entity can be properly supported or held by another entity’s stand or mounting system.
-
D.
hasSoftwareCompatibilityWith
Indicates that one software system can operate correctly and effectively with another software system, without conflicts or required modifications.
-
E.
compatiblePayload
Indicates that one entity can be safely or effectively used as the payload of another entity without conflict or required modification.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa457fc8190824ca00254e962f9 |
completed | March 8, 2026, 6:06 p.m. |
| PD | Predicate disambiguation | batch_69adae041d588190a84a02bca94adec8 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:16 p.m.