Triple
T37009561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silistra Municipality |
E915902
|
entity |
| Predicate | borderCountryAcrossDanube |
P97845
|
FINISHED |
| Object | Romania |
—
|
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: Romania | Statement: [Silistra Municipality, borderCountryAcrossDanube, Romania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderCountryAcrossDanube Context triple: [Silistra Municipality, borderCountryAcrossDanube, Romania]
-
A.
borderingCountryAcrossDanube
chosen
Indicates that one country shares a border with another country specifically across the Danube River.
-
B.
crossingOfDanube
Indicates a location or structure where a route, path, or connection passes across the Danube River.
-
C.
bordersAcrossRiver
Indicates that two regions or entities share a boundary with each other that is separated or defined by a river.
-
D.
borderLengthWithHungary_km
Indicates the length, in kilometers, of the border that an entity shares with Hungary.
-
E.
EUInternalBorder
Indicates that a border lies between two member states within the European Union, where internal EU border rules apply.
- F. None of above.
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_69f76e90ed548190b187d2475f5c807d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fff328ddc0819080642334a41fcf95 |
completed | May 10, 2026, 2:53 a.m. |
| PD | Predicate disambiguation | batch_69fff2e0971c819081aa66f4a6a34b28 |
completed | May 10, 2026, 2:52 a.m. |
Created at: May 3, 2026, 4:14 p.m.