Triple
T24533601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBC Broadcasting House, London |
E606882
|
entity |
| Predicate | housesProgramme |
P62094
|
FINISHED |
| Object | BBC Radio 4 Today programme |
—
|
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: BBC Radio 4 Today programme | Statement: [BBC Broadcasting House, London, housesProgramme, BBC Radio 4 Today programme]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: housesProgramme Context triple: [BBC Broadcasting House, London, housesProgramme, BBC Radio 4 Today programme]
-
A.
hostsPrograms
chosen
Indicates that one entity provides the venue, platform, or infrastructure for programs organized, run, or presented by another entity.
-
B.
domesticProgram
Indicates a program, initiative, or activity that operates within and is limited to a specific country’s internal context or territory.
-
C.
homeSeries
Indicates that one entity serves as the primary or home series to which another entity (such as an episode, installment, or related work) belongs.
-
D.
house1
Indicates that something is identified or classified as a house or dwelling.
-
E.
hasHomeProgram
Indicates that an entity is associated with or belongs to a primary or designated home program.
- 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_69e2c4c90c848190b23c4303620dcaaf |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:25 a.m.