Triple
T2298274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air New Zealand |
E51667
|
entity |
| Predicate | SkycouchDescription |
P38551
|
FINISHED |
| Object | row of economy seats that can be converted into a couch |
—
|
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: row of economy seats that can be converted into a couch | Statement: [Air New Zealand, SkycouchDescription, row of economy seats that can be converted into a couch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SkycouchDescription Context triple: [Air New Zealand, SkycouchDescription, row of economy seats that can be converted into a couch]
-
A.
cloudServiceName
Indicates the specific name assigned to a cloud-based service associated with an entity.
-
B.
storageLayer
Indicates a relationship where one entity functions as the storage layer or persistence tier used by another entity to store and retrieve data.
-
C.
hasCloudComposition
Indicates that an atmospheric body or region possesses a specific composition or makeup of clouds.
-
D.
storageOption
Indicates how or where something is stored, specifying the chosen method, medium, or configuration for its storage.
-
E.
supportsDatastoreType
Indicates that one entity is capable of working with, handling, or being compatible with a specified type of datastore.
- 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_69a88b0a9f248190bcff941463d8f65a |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abcbabf01081908db3b42bc7c60444 |
completed | March 7, 2026, 6:54 a.m. |
| PD | Predicate disambiguation | batch_69abc58ad33c8190b8d68af41b6f5e07 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcbab15488190bc8d2345f9d9f2bd |
completed | March 7, 2026, 6:54 a.m. |
Created at: March 4, 2026, 7:49 p.m.