Triple
T14275593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BAFTA TV Award for Best Entertainment Programme |
E353906
|
entity |
| Predicate | typicalNomineeFormat |
P16414
|
FINISHED |
| Object | television series |
—
|
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: television series | Statement: [BAFTA TV Award for Best Entertainment Programme, typicalNomineeFormat, television series]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalNomineeFormat Context triple: [BAFTA TV Award for Best Entertainment Programme, typicalNomineeFormat, television series]
-
A.
typicalNominees
Indicates that the specified entities are the usual or commonly selected candidates or recipients associated with something.
-
B.
typicalNumberOfNominees
Indicates the usual or standard count of nominees associated with something, such as an award, position, or selection process.
-
C.
nominationsAnnouncedBy
Indicates that one entity publicly announces or reveals the nominations associated with another entity.
-
D.
hasNomineeType
chosen
Indicates that an entity has a nominee belonging to a specified type or category.
-
E.
nominationsFrom
Indicates that one entity has put forward or proposed another entity as a candidate for a position, award, or recognition.
- 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_69d8278d25148190abf1a8c8f5f533ad |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6583f0ec81909ebfc7a2c6351ff8 |
completed | April 14, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69de2a88446481909cd526da97a3b70f |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:10 a.m.