Triple
T7033699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flash Video |
E163327
|
entity |
| Predicate | supportsStreamingProtocol |
P35980
|
FINISHED |
| Object | RTMP |
—
|
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: RTMP | Statement: [Flash Video, supportsStreamingProtocol, RTMP]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsStreamingProtocol Context triple: [Flash Video, supportsStreamingProtocol, RTMP]
-
A.
supportedProtocol
chosen
Indicates that one entity is compatible with, implements, or can operate using a specified communication or interaction protocol.
-
B.
supportsMultipleStreams
Indicates that the subject is capable of handling or maintaining more than one data or communication stream at the same time.
-
C.
supportsProgressiveDownload
Indicates that an entity enables or is compatible with progressive download, allowing data to be consumed while it is still being transferred.
-
D.
hasStreamingEligibility
Indicates that an entity is qualified or permitted to be made available via a streaming service or platform.
-
E.
supportsStreamingCompilation
Indicates that an entity is capable of performing compilation in a streaming manner, processing and compiling input incrementally as it is received rather than requiring the entire input up front.
- 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_69c6885d691c81908cf7d31083113886 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e458ad9c81908c3f492b317ce291 |
completed | March 27, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69c6e1b9a2488190aea351d96afa5a12 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:36 p.m.