Triple
T3458178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky Stream |
E72956
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Sky Glass |
E72563
|
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 Glass | Statement: [Sky Stream, relatedTo, Sky Glass]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sky Glass Context triple: [Sky Stream, relatedTo, Sky Glass]
-
A.
Sky Glass
chosen
Sky Glass is Sky’s integrated smart television platform that combines a 4K TV with built-in streaming, live TV, and voice control without requiring a satellite dish.
-
B.
Looking Glass
Looking Glass was a prominent Nez Perce leader and war chief who played a key strategic role during the Nez Perce War of 1877.
-
C.
Sky Mirror
Sky Mirror is a large, concave stainless-steel outdoor sculpture by Anish Kapoor that reflects and distorts the sky and surroundings like a giant mirror.
-
D.
Spectacles
Spectacles are Snap Inc.’s camera-equipped smart glasses designed to capture photos and videos hands-free for sharing on Snapchat.
-
E.
Sky Stream
Sky Stream is a streaming television service from Sky that delivers live TV and on-demand content over broadband without the need for a satellite dish.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbae36e748190bf20fd3c6de22e19 |
completed | March 8, 2026, 6:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b38bb904148190858af0bb467f5954 |
completed | March 13, 2026, 3:59 a.m. |
Created at: March 8, 2026, 3:16 p.m.