Triple
T12789516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IK-3 |
E305719
|
entity |
| Predicate | designCompany |
P25389
|
FINISHED |
| Object | Rogožarski |
E305718
|
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: Rogožarski | Statement: [IK-3, designCompany, Rogožarski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rogožarski Context triple: [IK-3, designCompany, Rogožarski]
-
A.
Rogožarski
chosen
Rogožarski was a Yugoslav aircraft manufacturer known for producing military and trainer aircraft in the interwar and World War II periods.
-
B.
Orebić
Orebić is a coastal town on Croatia’s Pelješac Peninsula, known as a popular ferry gateway to the island of Korčula and for its beaches and maritime heritage.
-
C.
Plesac
Plesac is a surname most notably associated with former Major League Baseball pitcher and current broadcaster Dan Plesac.
-
D.
Rožaje
Rožaje is a small mountainous town in northeastern Montenegro, known for its Bosniak-majority population and role as a cultural and economic center of the Sandžak region.
-
E.
Plešnar
Plešnar is a Slovenian surname most notably borne by the photographer Zora Plešnar.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6a61f48190972e241e70bc392c |
completed | April 10, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69b925b3c81909f5e604c0f457645 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:30 p.m.