Triple
T37013530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skytrax Airline of the Year 2016 |
E916012
|
entity |
| Predicate | winnerAirline |
P9049
|
FINISHED |
| Object | Emirates |
—
|
NE NERFINISHED |
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: Emirates | Statement: [Skytrax Airline of the Year 2016, winnerAirline, Emirates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winnerAirline Context triple: [Skytrax Airline of the Year 2016, winnerAirline, Emirates]
-
A.
airlineUsed
Indicates that a particular airline is employed or chosen for transporting someone or something in a given trip or flight.
-
B.
airline
chosen
Indicates that an entity operates as a commercial air transport carrier providing flight services between locations.
-
C.
winningFlightDate
Indicates the date on which the associated flight is determined to be the winning or selected one among a set of candidate flights.
-
D.
ownsAirline
Indicates that one entity has legal ownership or controlling interest in an airline company.
-
E.
flightPartner
Indicates that two entities are associated as partners in operating, marketing, or coordinating a flight or set of flights.
- 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_69f76e90ed548190b187d2475f5c807d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: May 3, 2026, 4:14 p.m.