Triple
T6925292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drina |
E160289
|
entity |
| Predicate | passesNear |
P416
|
FINISHED |
| Object |
Zvornik
Zvornik is a historic town and municipality in northeastern Bosnia and Herzegovina, situated on the banks of the Drina River near the border with Serbia.
|
E634200
|
NE FINISHED |
How this triple was built (4 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: Zvornik | Statement: [Drina, passesNear, Zvornik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zvornik Context triple: [Drina, passesNear, Zvornik]
-
A.
Konjic
Konjic is a historic town in central Bosnia and Herzegovina known for its scenic setting on the Neretva River and its Ottoman-era stone bridge.
-
B.
Jasenica
Jasenica is a river in central Serbia that flows through the Šumadija region before joining the Velika Morava.
-
C.
Bihać
Bihać is a city in northwestern Bosnia and Herzegovina that became internationally known during the Bosnian War as a besieged enclave and designated UN "safe area."
-
D.
Mladenovac
Mladenovac is a suburban municipality and town located in the southern part of the City of Belgrade, Serbia.
-
E.
Jablanica
Jablanica is a town in Bosnia and Herzegovina known for its location in the Neretva River valley and its historical World War II railway bridge.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Zvornik Triple: [Drina, passesNear, Zvornik]
Generated description
Zvornik is a historic town and municipality in northeastern Bosnia and Herzegovina, situated on the banks of the Drina River near the border with Serbia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Zvornik Target entity description: Zvornik is a historic town and municipality in northeastern Bosnia and Herzegovina, situated on the banks of the Drina River near the border with Serbia.
-
A.
Konjic
Konjic is a historic town in central Bosnia and Herzegovina known for its scenic setting on the Neretva River and its Ottoman-era stone bridge.
-
B.
Jasenica
Jasenica is a river in central Serbia that flows through the Šumadija region before joining the Velika Morava.
-
C.
Bihać
Bihać is a city in northwestern Bosnia and Herzegovina that became internationally known during the Bosnian War as a besieged enclave and designated UN "safe area."
-
D.
Mladenovac
Mladenovac is a suburban municipality and town located in the southern part of the City of Belgrade, Serbia.
-
E.
Jablanica
Jablanica is a town in Bosnia and Herzegovina known for its location in the Neretva River valley and its historical World War II railway bridge.
- F. None of above. chosen
Provenance (5 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_69c6884d350081908d8a970e4d40ad78 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6da18b6388190947dfc1eb9e5d382 |
completed | March 27, 2026, 7:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c769f6340c8190adab3e28cfe67e4a |
completed | March 28, 2026, 5:41 a.m. |
| NEDg | Description generation | batch_69c76afe5cf481909cb22ebf94511530 |
completed | March 28, 2026, 5:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c76b690e3c8190823cb5cda4e3f5ac |
completed | March 28, 2026, 5:47 a.m. |
Created at: March 27, 2026, 2:26 p.m.