Triple
T17806794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schilthorn |
E444583
|
entity |
| Predicate | hasRevolvingRestaurant |
P52138
|
FINISHED |
| Object | Piz Gloria |
—
|
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: Piz Gloria | Statement: [Schilthorn, hasRevolvingRestaurant, Piz Gloria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piz Gloria Context triple: [Schilthorn, hasRevolvingRestaurant, Piz Gloria]
-
A.
Piz Gloria
chosen
Piz Gloria is a revolving restaurant and tourist attraction in the Swiss Alps, famously featured in the James Bond film "On Her Majesty's Secret Service."
-
B.
Piz Boè
Piz Boè is a prominent mountain peak in the Dolomites of northern Italy, popular with hikers and climbers for its panoramic alpine views.
-
C.
Piz Ot
Piz Ot is a mountain peak in the Albula Alps of eastern Switzerland, known for its panoramic views over the Engadin region.
-
D.
Piz d’Err
Piz d’Err is a mountain peak in the Albula Alps of eastern Switzerland, known for its rugged terrain and scenic alpine surroundings.
-
E.
Piz Pisoc
Piz Pisoc is a prominent mountain peak in the Swiss Alps located in the canton of Graubünden.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e488044cdc8190a09a2265c8a86475 |
completed | April 19, 2026, 7:45 a.m. |
Created at: April 10, 2026, 10:14 a.m.