Triple
T18313373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karlovac |
E438687
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Dobra |
—
|
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: Dobra | Statement: [Karlovac, locatedOnRiver, Dobra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dobra Context triple: [Karlovac, locatedOnRiver, Dobra]
-
A.
Dobra
chosen
Dobra is a river in central Croatia known for flowing through Karlovac County and contributing to the region’s karst landscape and hydropower resources.
-
B.
dobra
The dobra is the official monetary unit of São Tomé and Príncipe, a small island nation off the west coast of Central Africa.
-
C.
Dobrada
Dobrada is a small municipality in the state of São Paulo, Brazil, known for its agricultural economy and rural character.
-
D.
Dobrota
Dobrota is a coastal town in Montenegro known for its historic stone houses and scenic waterfront along the Bay of Kotor.
-
E.
Gutes
The Gutes were the North Germanic inhabitants of the Baltic island of Gotland, known for their distinct Gutnish language and extensive Viking Age trade networks.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5021a96b48190976273be3ff3e5c6 |
completed | April 19, 2026, 4:26 p.m. |
Created at: April 10, 2026, 10:36 a.m.