Triple
T1722011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Airbus A300 |
E37411
|
entity |
| Predicate | usedBy |
P260
|
FINISHED |
| Object | DHL Aviation |
E177498
|
NE 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: DHL Aviation | Statement: [Airbus A300, usedBy, DHL Aviation]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DHL Aviation Context triple: [Airbus A300, usedBy, DHL Aviation]
-
A.
DHL Aviation
chosen
DHL Aviation is the air cargo division of DHL, operating a global network of freight flights that connect major logistics hubs worldwide.
-
B.
Orix Aviation
Orix Aviation is a global aircraft leasing and asset management company that provides financing and fleet solutions to airlines worldwide.
-
C.
Peach Aviation
Peach Aviation is a Japanese low-cost airline based in Osaka that operates domestic and international flights primarily across East Asia.
-
D.
Mahan Air
Mahan Air is a major Iranian private airline that operates domestic and international flights across Asia, Europe, and the Middle East.
-
E.
Republic Airways
Republic Airways is a U.S. regional airline that operates feeder flights for major carriers under various brand agreements.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a8861acab88190bb43cde203429399 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa635703dc8190809260de43b72ea3 |
completed | March 6, 2026, 5:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada0d58cd08190bdda9f03ca458081 |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 4, 2026, 7:30 p.m.