Triple
T11357169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Split Airport |
E268985
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Kaštela |
E920911
|
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: Kaštela | Statement: [Split Airport, nearbyCity, Kaštela]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaštela Context triple: [Split Airport, nearbyCity, Kaštela]
-
A.
Kaštela
chosen
Kaštela is a coastal town in Dalmatia, Croatia, situated along the Adriatic Sea near Split and known for its string of historic settlements and proximity to Split Airport.
-
B.
Kastel
Kastel is a district of Mainz in Germany, historically part of the Rhine river region and known as the birthplace of brewing magnate Adolphus Busch.
-
C.
Fortress Kaštel
Fortress Kaštel is a historic Venetian-era hilltop fortification in Pula, Croatia, offering panoramic views of the city and its harbor.
-
D.
Krusevac
Krusevac is a historic city in central Serbia that once served as the medieval capital under Prince Lazar and is now an important regional industrial and cultural center.
-
E.
Tvrđa
Tvrđa is the well-preserved baroque fortress and old town district of Osijek, known for its historic architecture and cultural heritage.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea419afc8190b3a93141d015ebdf |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5564d5a8c81908bddbf3f771370f7 |
completed | April 19, 2026, 10:25 p.m. |
Created at: April 8, 2026, 9:33 p.m.