Triple
T19364801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EB |
E484373
|
entity |
| Predicate | regionalUnit |
P766
|
FINISHED |
| Object | Evros |
—
|
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: Evros | Statement: [EB, regionalUnit, Evros]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evros Context triple: [EB, regionalUnit, Evros]
-
A.
Evros
chosen
Evros is a regional unit in northeastern Greece bordering Turkey and Bulgaria, known for its namesake river and strategic geopolitical location.
-
B.
Evros Delta
Evros Delta is a biologically rich wetland area at the mouth of the Evros River, known for its diverse birdlife and ecological importance on the border between Greece and Turkey.
-
C.
Evrostina
Evrostina is a village in the Corinthia region of the Peloponnese in Greece, known for its mountainous landscape and traditional character.
-
D.
Nea Erythraia
Nea Erythraia is a suburban area in the northern part of the Athens metropolitan region in Greece, known for its residential character and proximity to Kifisia.
-
E.
Roumeli
Roumeli is a historical region in central Greece that played a key role in the Greek War of Independence.
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e619aa9ff48190b1ede47fb88a682e |
completed | April 20, 2026, 12:18 p.m. |
Created at: April 10, 2026, 1:35 p.m.