Triple
T3176403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hainan Airlines |
E66474
|
entity |
| Predicate | SkytraxRating |
P45660
|
FINISHED |
| Object | 5-star airline |
—
|
LITERAL 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: 5-star airline | Statement: [Hainan Airlines, SkytraxRating, 5-star airline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SkytraxRating Context triple: [Hainan Airlines, SkytraxRating, 5-star airline]
-
A.
hasTourismRating
Indicates that an entity has been assigned a specific tourism-related quality or rating, reflecting its appeal or suitability for tourists.
-
B.
airlineSafetyReputation
Indicates the perceived level of safety and reliability associated with an airline’s operations and history.
-
C.
airportRank
Indicates the relative position or level assigned to an airport within a ranking or ordered list.
-
D.
hasTouristRank
Indicates that an entity is assigned a specific rank or rating based on its attractiveness or importance as a tourist destination.
-
E.
hasPassengerTrafficRank
Indicates the relative position or ranking of an entity based on the volume of passenger traffic it handles compared to others.
- F. None of above. chosen
Provenance (4 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada69b0bec8190957913b44d876079 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e02677c8190a21d93b1259b2761 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f7c21c819087e9992f5fe30a37 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:06 p.m.