Triple
T19925866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goražde |
E478920
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Drina |
—
|
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: Drina | Statement: [Goražde, locatedOnRiver, Drina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drina Context triple: [Goražde, locatedOnRiver, Drina]
-
A.
Drina
chosen
The Drina is a significant river in the western Balkans, forming much of the border between Bosnia and Herzegovina and Serbia and known for its scenic canyons and historical importance.
-
B.
Kolubara
Kolubara is a river in western Serbia known for flowing through the Kolubara coal basin before joining the Sava River.
-
C.
Crvena Reka
Crvena Reka is a smaller river in southeastern Serbia that serves as one of the tributaries feeding into the Nišava River.
-
D.
Neretva
Neretva is a major river in the western Balkans, known for its emerald-green waters, deep canyons, and historic bridges such as the Stari Most in Mostar.
-
E.
Sava
Sava is a town and comune in the Province of Taranto in the Apulia region of southern Italy, known for its wine and olive oil production.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c992fc8190bd262d528be0e636 |
completed | April 20, 2026, 4:52 p.m. |
Created at: April 10, 2026, 1:53 p.m.