Triple
T10739665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Business Premier |
E253286
|
entity |
| Predicate | cabinClassBelow |
P95735
|
FINISHED |
| Object | First Class (not offered by Air New Zealand) |
—
|
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: First Class (not offered by Air New Zealand) | Statement: [Business Premier, cabinClassBelow, First Class (not offered by Air New Zealand)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cabinClassBelow Context triple: [Business Premier, cabinClassBelow, First Class (not offered by Air New Zealand)]
-
A.
hasCabinClass
Indicates that an entity (such as a booking, ticket, or seat) is associated with a specific cabin class (e.g., economy, business, first).
-
B.
comfortLevelComparedToPremiumCabins
Indicates how the comfort level of something compares relative to that of premium cabins.
-
C.
seatClass
Indicates the travel or seating category assigned to a passenger or seat (e.g., economy, business, first class).
-
D.
cabinConfiguration
Indicates how the interior space of a vehicle, vessel, or aircraft is arranged and organized for occupants or cargo.
-
E.
cabinTypes
Indicates the types or categories of cabins associated with an entity, such as the different classes or configurations available.
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d71043106c819091939950f532eda5 |
completed | April 9, 2026, 2:34 a.m. |
| PD | Predicate disambiguation | batch_69d6f30df9948190ab3cdc33977fac14 |
completed | April 9, 2026, 12:30 a.m. |
| PDg | Predicate description generation | batch_69d6fa323564819097b207eb53f8a9b8 |
completed | April 9, 2026, 1 a.m. |
Created at: April 8, 2026, 9:14 p.m.