Triple
T7827147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Sedaris |
E181274
|
entity |
| Predicate | hasWrittenFor |
P11775
|
FINISHED |
| Object | BBC Radio 4 |
E12973
|
NE 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: BBC Radio 4 | Statement: [David Sedaris, hasWrittenFor, BBC Radio 4]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BBC Radio 4 Context triple: [David Sedaris, hasWrittenFor, BBC Radio 4]
-
A.
BBC Radio 4
chosen
BBC Radio 4 is a major British national radio station known for its spoken-word programming, including news, drama, comedy, and documentaries.
-
B.
BBC Radio
BBC Radio is the British Broadcasting Corporation’s portfolio of national and local radio stations in the United Kingdom, covering a wide range of music, speech, news, and cultural programming.
-
C.
BBC Radio 4 Extra
BBC Radio 4 Extra is a British digital radio station from the BBC that specializes in archived comedy, drama, and entertainment programming.
-
D.
BBC Radio 7
BBC Radio 7 was a British digital radio station specializing in comedy, drama, and entertainment programming from the BBC archives.
-
E.
BBC Sounds
BBC Sounds is the BBC’s digital audio platform offering live radio, music mixes, and podcasts across web and mobile apps.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8282ccec819083c48efb72d21cf9 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb04a7f3b8819080f8a8283d6118fb |
completed | March 30, 2026, 11:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5a797ee881908068ba7346042756 |
completed | March 31, 2026, 5:24 a.m. |
Created at: March 30, 2026, 4:43 p.m.