Triple
T1946908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheremetyevo International Airport |
E42073
|
entity |
| Predicate | servesAsHubFor |
P423
|
FINISHED |
| Object | Pegas Fly |
E42074
|
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: Pegas Fly | Statement: [Sheremetyevo International Airport, servesAsHubFor, Pegas Fly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pegas Fly Context triple: [Sheremetyevo International Airport, servesAsHubFor, Pegas Fly]
-
A.
Pegas Fly
chosen
Pegas Fly is a Russian airline that operates domestic and international passenger flights, using Sheremetyevo International Airport as one of its main bases.
-
B.
Swoop
Swoop is the Philadelphia Eagles’ official bald eagle mascot, known for entertaining fans at games and team events.
-
C.
Swoop
Swoop is the red-tailed hawk mascot representing the University of Utah’s athletic teams.
-
D.
Flying J
Flying J is a chain of highway travel centers and truck stops in North America, known for providing fuel, food, and amenities for professional drivers and motorists.
-
E.
Wing
Wing is an experimental mobile operating system and user interface project developed by X (formerly Google X) to explore new paradigms in smartphone interaction and design.
- 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_69a8870e08fc8190a319cbf2600db15f |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb32ebae881908f7541301f0198ae |
completed | March 7, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae03180a248190a0df96066923728a |
completed | March 8, 2026, 11:15 p.m. |
Created at: March 4, 2026, 7:36 p.m.