Triple
T543598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danube |
E12683
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object | Morava |
E75220
|
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: Morava | Statement: [Danube, hasTributary, Morava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Morava Context triple: [Danube, hasTributary, Morava]
-
A.
Fiumana
Fiumana is a small locality in the municipality of Predappio in the Emilia-Romagna region of northern Italy.
-
B.
Gera
Gera is a city in the German state of Thuringia, known for its industrial heritage and historic architecture along the White Elster river.
-
C.
Savo
Savo is a town in Kenya’s Central Province known as one of the region’s notable settlements.
-
D.
Magdalena
Magdalena is the given first name of Swedish opera singer and environmental activist Malena Ernman.
-
E.
Sava
chosen
Sava is a major river in Central and Southeastern Europe that flows through countries including Slovenia, Croatia, Bosnia and Herzegovina, and Serbia before joining the Danube.
- 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_69a49334226c81908b0ea1689ef6aa3f |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a498dea88881908a938fe8f2313bec |
completed | March 1, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a523853a648190bdf48e8148fa642b |
completed | March 2, 2026, 5:43 a.m. |
Created at: March 1, 2026, 7:32 p.m.