Triple
T1398389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SkyTeam |
E30721
|
entity |
| Predicate | benefitForPassengers |
P487
|
FINISHED |
| Object | single-ticket itineraries across multiple airlines |
—
|
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: single-ticket itineraries across multiple airlines | Statement: [SkyTeam, benefitForPassengers, single-ticket itineraries across multiple airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: benefitForPassengers Context triple: [SkyTeam, benefitForPassengers, single-ticket itineraries across multiple airlines]
-
A.
passengers
Indicates that one entity is traveling in or being transported by another entity, typically as a non-operating occupant.
-
B.
hasPassengerServicesTo
Indicates that a transportation provider operates passenger services connecting one location or entity to another.
-
C.
hasPassengerHandling
Indicates that an entity is responsible for or involved in managing the processes and services related to handling passengers.
-
D.
formerPassengerService
Indicates that an entity previously provided passenger transportation services but no longer does so.
-
E.
benefits
chosen
Indicates that one entity gains an advantage, improvement, or positive outcome as a result of another entity or action.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c382b6588190833c39ac84fb6139 |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.