Triple
T5887341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calgary Tower |
E130895
|
entity |
| Predicate | hasRestaurant |
P4442
|
FINISHED |
| Object |
Sky 360
Sky 360 is a revolving restaurant located atop the Calgary Tower, offering panoramic views of Calgary and its surroundings.
|
E554217
|
NE FINISHED |
How this triple was built (4 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 360 | Statement: [Calgary Tower, hasRestaurant, Sky 360]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sky 360 Context triple: [Calgary Tower, hasRestaurant, Sky 360]
-
A.
Sky (satellite television)
Sky (satellite television) is a major British pay-TV and broadcasting service offering a wide range of channels, on-demand content, and subscription packages via satellite.
-
B.
Cloud 9
Cloud 9 is a world-famous surf break on Siargao Island in the Philippines, renowned for its powerful barreling waves and annual international surfing competitions.
-
C.
SKYPASS
SKYPASS is Korean Air’s loyalty program that rewards frequent flyers with miles redeemable for flights, upgrades, and other travel benefits.
-
D.
Skylink
Skylink is an automated people mover system that transports passengers between terminals at Dallas/Fort Worth International Airport.
-
E.
SkyPod
SkyPod is the highest observation deck of Toronto’s CN Tower, offering panoramic views from near the top of the landmark skyscraper.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sky 360 Triple: [Calgary Tower, hasRestaurant, Sky 360]
Generated description
Sky 360 is a revolving restaurant located atop the Calgary Tower, offering panoramic views of Calgary and its surroundings.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sky 360 Target entity description: Sky 360 is a revolving restaurant located atop the Calgary Tower, offering panoramic views of Calgary and its surroundings.
-
A.
Sky (satellite television)
Sky (satellite television) is a major British pay-TV and broadcasting service offering a wide range of channels, on-demand content, and subscription packages via satellite.
-
B.
Cloud 9
Cloud 9 is a world-famous surf break on Siargao Island in the Philippines, renowned for its powerful barreling waves and annual international surfing competitions.
-
C.
SKYPASS
SKYPASS is Korean Air’s loyalty program that rewards frequent flyers with miles redeemable for flights, upgrades, and other travel benefits.
-
D.
Skylink
Skylink is an automated people mover system that transports passengers between terminals at Dallas/Fort Worth International Airport.
-
E.
SkyPod
SkyPod is the highest observation deck of Toronto’s CN Tower, offering panoramic views from near the top of the landmark skyscraper.
- F. None of above. chosen
Provenance (5 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0367a61648190bf97746caa4061fe |
completed | March 22, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0b141a93081908ad4a64f9a96dce4 |
completed | March 23, 2026, 3:19 a.m. |
| NEDg | Description generation | batch_69c0b22d661c8190a055abd3ca6fa92f |
completed | March 23, 2026, 3:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0b608a10881908c9bca7d09a99b05 |
completed | March 23, 2026, 3:39 a.m. |
Created at: March 22, 2026, 3:57 p.m.