Triple
T14253214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBC Four +1 |
E353320
|
entity |
| Predicate | broadcastPlatform |
P17479
|
FINISHED |
| Object | Sky (UK and Ireland) |
E15019
|
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: Sky (UK and Ireland) | Statement: [BBC Four +1, broadcastPlatform, Sky (UK and Ireland)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sky (UK and Ireland) Context triple: [BBC Four +1, broadcastPlatform, Sky (UK and Ireland)]
-
A.
Sky (UK and Ireland)
chosen
Sky (UK and Ireland) is a major satellite television and telecommunications provider serving customers across the United Kingdom and Ireland.
-
B.
SKY
SKY is the ICAO airline designator used to identify Skymark Airlines in international aviation operations.
-
C.
SKY
SKY is the Amtrak station code for Sandusky station in Sandusky, Ohio, used for passenger rail ticketing and scheduling.
-
D.
UK 24/7
UK 24/7 is a large-scale photographic project and book capturing a day in the life of the United Kingdom through images taken over a 24-hour period, created under the direction of photographer Rick Smolan.
-
E.
Sky Deutschland
Sky Deutschland is a German pay television and streaming provider offering premium sports, film, and entertainment channels to subscribers in Germany and Austria.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6297f38c819090d7c7fd8bfa2e9e |
completed | April 14, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd325c98288190ba035fb5cc5bcf6b |
completed | May 8, 2026, 12:46 a.m. |
Created at: April 10, 2026, 1:09 a.m.