Triple
T18917939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CKFM-FM |
E462767
|
entity |
| Predicate | formerBranding |
P1501
|
FINISHED |
| Object | 99.9 Mix FM |
—
|
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: 99.9 Mix FM | Statement: [CKFM-FM, formerBranding, 99.9 Mix FM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 99.9 Mix FM Context triple: [CKFM-FM, formerBranding, 99.9 Mix FM]
-
A.
Kiss FM
Kiss FM is a popular radio station brand known for broadcasting contemporary hit music and dance tracks, often featuring prominent DJs and club culture programming.
-
B.
CKFM-FM
chosen
CKFM-FM is a Toronto-based Canadian radio station, best known as the contemporary hit music outlet branded as 99.9 Virgin Radio.
-
C.
Big 98.1
Big 98.1 is a Philadelphia-area FM radio station brand known for playing classic hits and oldies.
-
D.
Jack FM
Jack FM is a Canadian radio network brand known for its adult hits format and slogan “playing what we want,” featuring a wide variety of popular music from past decades.
-
E.
WEEP-FM
WEEP-FM was a Pittsburgh-area radio station best known for its longtime country music format before changing its call sign to WDSY-FM.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c62884988190a362ada1a0a47134 |
completed | April 20, 2026, 6:22 a.m. |
Created at: April 10, 2026, 11:59 a.m.