Triple
T35719285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CCIR System D |
E1032422
|
entity |
| Predicate | transmissionStandardType |
P15185
|
FINISHED |
| Object | broadcast television |
—
|
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: broadcast television | Statement: [CCIR System D, transmissionStandardType, broadcast television]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transmissionStandardType Context triple: [CCIR System D, transmissionStandardType, broadcast television]
-
A.
transmissionType
Indicates the method or medium through which something is transmitted or conveyed from one entity to another.
-
B.
transmissionStandard
chosen
Indicates the communication or signal protocol used to transmit data or content between systems or devices.
-
C.
transmissionTypeSupported
Indicates that a particular type of transmission is compatible with or can be used by a given system, device, or component.
-
D.
transmissionClass
Indicates the type or category of transmission mechanism associated with an entity (e.g., how power or signals are conveyed or transferred).
-
E.
transmissionCategory
Indicates the mode or type of transmission through which something (e.g., a signal, disease, or data) is passed from one source to another.
- 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_69f76e102b5881909e5d63a30a5cecbe |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:05 p.m.