Triple
T34859514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tripoint of Bulgaria–Greece–Turkey |
E1004825
|
entity |
| Predicate | nonEUCountryAtPoint |
P167902
|
FINISHED |
| Object | Turkey |
—
|
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: Turkey | Statement: [tripoint of Bulgaria–Greece–Turkey, nonEUCountryAtPoint, Turkey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nonEUCountryAtPoint Context triple: [tripoint of Bulgaria–Greece–Turkey, nonEUCountryAtPoint, Turkey]
-
A.
nonEUCountryOnOneSide
chosen
Indicates that at least one party or side involved in the relationship is a country that is not a member of the European Union.
-
B.
countryPortionIn
Indicates that a specific part or region is located within the boundaries of a particular country.
-
C.
isInEuropeanUnionCountry
Indicates that the subject entity is located within, or belongs to, a country that is a member of the European Union.
-
D.
countryContains
Indicates that a country geographically encompasses or includes a specified location, region, or entity within its borders.
-
E.
nearDetectorCountry
Indicates that the subject entity is geographically close to the country where the detector is located.
- 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_69f76dbb678081909a247b9b5e1a73ac |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f782f4f10081908f97f6d0d2dbeec7 |
completed | May 3, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69f780ff71cc8190a67e71076fbad81a |
completed | May 3, 2026, 5:08 p.m. |
Created at: May 3, 2026, 4 p.m.