Triple
T15884931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morava river system |
E385167
|
entity |
| Predicate | majorRiver |
P165
|
FINISHED |
| Object | Moravica |
—
|
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: Moravica | Statement: [Morava river system, majorRiver, Moravica]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moravica Context triple: [Morava river system, majorRiver, Moravica]
-
A.
Moravica
chosen
Moravica is a river in central Serbia that serves as a significant left-bank tributary of the West Morava.
-
B.
West Morava
West Morava is a major river in central Serbia that serves as one of the two principal headwaters of the Velika Morava.
-
C.
South Morava
South Morava is a major river in southeastern Serbia that flows northward through the Morava Valley and serves as one of the principal tributaries forming the Velika Morava.
-
D.
Morača
Morača is a major river in Montenegro that flows through the capital city of Podgorica before emptying into Lake Skadar.
-
E.
Vrbas
Vrbas is a river in western Bosnia and Herzegovina that flows through cities like Banja Luka before joining the Sava River.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1561997bc8190a40e7d68defbbddd |
completed | April 16, 2026, 9:35 p.m. |
Created at: April 10, 2026, 4:51 a.m.