Triple
T12478441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moscow–Havana |
E298236
|
entity |
| Predicate | operatedBy |
P86
|
FINISHED |
| Object | Aeroflot |
E18861
|
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: Aeroflot | Statement: [Moscow–Havana, operatedBy, Aeroflot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aeroflot Context triple: [Moscow–Havana, operatedBy, Aeroflot]
-
A.
Aeroflot
chosen
Aeroflot is Russia's largest and flag-carrying airline, headquartered in Moscow and operating an extensive network of domestic and international flights.
-
B.
Rossiya Airlines
Rossiya Airlines is a Russian airline based in Saint Petersburg that operates domestic and international passenger flights as part of the Aeroflot Group.
-
C.
Ural Airlines
Ural Airlines is a Russian airline based in Yekaterinburg that operates domestic and international passenger flights across Europe, Asia, and the Middle East.
-
D.
Aerosvit Airlines
Aerosvit Airlines was a now-defunct Ukrainian carrier that operated domestic and international flights, primarily from its main base in Kyiv.
-
E.
Arkhangelsk Airlines
Arkhangelsk Airlines was a Russian regional airline based in Arkhangelsk that later became known as Nordavia.
- 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_69d6ada377208190a36011199a4d8558 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94dcc24e48190ae9c367a03f659f4 |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67188f6b481909885e35dce5a5b69 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 8, 2026, 9:56 p.m.