Triple
T34859486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tripoint of Bulgaria–Greece–Turkey |
E1004825
|
entity |
| Predicate | riverNameInGreek |
P182306
|
FINISHED |
| Object | Έβρος |
—
|
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: Έβρος | Statement: [tripoint of Bulgaria–Greece–Turkey, riverNameInGreek, Έβρος]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverNameInGreek Context triple: [tripoint of Bulgaria–Greece–Turkey, riverNameInGreek, Έβρος]
-
A.
hydronymOf
Indicates that one term is the name of a body of water associated with another geographic entity (e.g., a river, lake, or sea named after a place or feature).
-
B.
mouthOfTheWatercourse
Indicates the location where a watercourse ends and flows into a larger body of water.
-
C.
raceRiver
Indicates that an entity participates in a race that takes place on or along a river.
-
D.
riverSystemNameInRomanian
Indicates that a river system is referred to by a specific name in the Romanian language.
-
E.
isWatercourseOf
Indicates that a watercourse (such as a river or stream) flows through, belongs to, or is geographically associated with a particular area or feature.
- F. None of above. chosen
Provenance (4 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_69f76dbb678081909a247b9b5e1a73ac |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69f7886b27f08190ab4580f949222c93 |
completed | May 3, 2026, 5:39 p.m. |
Created at: May 3, 2026, 4 p.m.