Triple
T8833397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burgas Bay |
E210200
|
entity |
| Predicate | hasNearbyAirport |
P4363
|
FINISHED |
| Object | Burgas Airport |
E210199
|
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: Burgas Airport | Statement: [Burgas Bay, hasNearbyAirport, Burgas Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burgas Airport Context triple: [Burgas Bay, hasNearbyAirport, Burgas Airport]
-
A.
Burgas Airport
chosen
Burgas Airport is an international airport on Bulgaria’s Black Sea coast that serves the city of Burgas and nearby seaside resorts.
-
B.
Plovdiv Airport
Plovdiv Airport is an international airport in southern Bulgaria serving the city of Plovdiv and the surrounding region, including access to nearby ski resorts.
-
C.
Varna Airport
Varna Airport is an international airport serving the city of Varna and the surrounding Black Sea resort region in Bulgaria.
-
D.
Sofia Airport
Sofia Airport is the main international airport serving Bulgaria’s capital city, Sofia, and one of the country’s busiest air transport hubs.
-
E.
Platov International Airport
Platov International Airport is a major modern airport serving the city of Rostov-on-Don and the surrounding region in southern Russia.
- 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_69ca8388549c819095fd94eadefbb007 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60670fa48190b2a873f6498de7f6 |
completed | April 1, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfab71962c8190823a1ca1d4fa56f3 |
completed | April 3, 2026, 11:58 a.m. |
Created at: March 30, 2026, 6:47 p.m.