Triple
T11237700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EVA Air |
E265984
|
entity |
| Predicate | offersCabinFeature |
P79291
|
FINISHED |
| Object | lie-flat business class seats on long-haul flights |
—
|
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: lie-flat business class seats on long-haul flights | Statement: [EVA Air, offersCabinFeature, lie-flat business class seats on long-haul flights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersCabinFeature Context triple: [EVA Air, offersCabinFeature, lie-flat business class seats on long-haul flights]
-
A.
cabinConfiguration
Indicates how the interior space of a vehicle, vessel, or aircraft is arranged and organized for occupants or cargo.
-
B.
amenitiesInclude
chosen
Indicates that a place or facility provides or contains specific amenities as part of its features.
-
C.
hasCabins
Indicates that an entity possesses or includes one or more cabins as part of its structure or facilities.
-
D.
cabinTypes
Indicates the types or categories of cabins associated with an entity, such as the different classes or configurations available.
-
E.
hasCampingOption
Indicates that an entity offers or includes the possibility to camp (e.g., designated camping facilities or areas).
- F. None of above.
Provenance (3 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_69d6aac656d48190b275efaa7d6074ee |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e918375081908c2a7ccb50cbf331 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d7878906f48190b63ddc103a0c8f9b |
completed | April 9, 2026, 11:03 a.m. |
Created at: April 8, 2026, 9:30 p.m.