Triple
T17809385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trogir |
E444656
|
entity |
| Predicate | hasAirportAccessVia |
P4363
|
FINISHED |
| Object | Split Airport |
—
|
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: Split Airport | Statement: [Trogir, hasAirportAccessVia, Split Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Split Airport Context triple: [Trogir, hasAirportAccessVia, Split Airport]
-
A.
Split Airport
chosen
Split Airport is an international airport on Croatia’s Dalmatian coast serving the city of Split and the surrounding Adriatic tourist region.
-
B.
Flughafen
Flughafen is the Nuremberg U-Bahn station that serves Nuremberg Airport, providing direct metro access between the airport and the city.
-
C.
Aeroport
Aeroport is a Moscow Metro station on the Zamoskvoretskaya Line, named after the nearby Khodynka Aerodrome area.
-
D.
Airport Spur
Airport Spur is a segment of the Constitution Trail that branches off to provide a dedicated multi-use path connection toward the local airport area.
-
E.
Terminal Aérea
Terminal Aérea is a Mexico City Metro station that serves the area around the Mexico City International Airport, providing convenient transit access for air travelers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4887976e48190842840ef064dc772 |
completed | April 19, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:14 a.m.