Triple
T37164045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISDB |
E920747
|
entity |
| Predicate | ITURecommendation |
P34894
|
FINISHED |
| Object | ITU-R BT.1306 |
—
|
NE NERFINISHED |
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: ITU-R BT.1306 | Statement: [ISDB, ITURecommendation, ITU-R BT.1306]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ITURecommendation Context triple: [ISDB, ITURecommendation, ITU-R BT.1306]
-
A.
supportsMobileTVStandard
Indicates that one entity is compatible with or implements a specified mobile TV broadcasting standard for use on mobile devices.
-
B.
recommendsUseOf
chosen
Indicates that one entity advises, endorses, or suggests the use of another entity as appropriate or beneficial in a given context.
-
C.
mediaAdaptationSettingOf
Indicates that a media adaptation (such as a film, series, or game) is set in the narrative world or environment of a particular original work.
-
D.
recommendedWiFiStandard
Indicates that one entity suggests or endorses a particular WiFi standard as the preferred option for another entity or context.
-
E.
recommendedForNewSystems
Indicates that something is advised or preferred to be used when designing or implementing new systems, rather than existing or legacy ones.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.