Triple
T34859494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tripoint of Bulgaria–Greece–Turkey |
E1004825
|
entity |
| Predicate | countrySubdivisionBulgaria |
P203455
|
FINISHED |
| Object | Haskovo Province |
—
|
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: Haskovo Province | Statement: [tripoint of Bulgaria–Greece–Turkey, countrySubdivisionBulgaria, Haskovo Province]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countrySubdivisionBulgaria Context triple: [tripoint of Bulgaria–Greece–Turkey, countrySubdivisionBulgaria, Haskovo Province]
-
A.
onlyBulgarianSettlementWithin
Indicates that a settlement is the only Bulgarian settlement located within a specified containing area or region.
-
B.
distanceFromSofia
Indicates the spatial distance between a given entity and the city of Sofia.
-
C.
nearVillageInBulgaria
Indicates that one entity is located close to a village situated within the country of Bulgaria.
-
D.
distanceToBulgarianBorder_km
Indicates the distance, measured in kilometers, from a given location to the nearest point on the Bulgarian national border.
-
E.
borderTypeToBulgaria
Indicates the type or nature of the border that an entity shares with Bulgaria.
- 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_6a01839b071481909f9cc79a6a09387d |
completed | May 11, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_6a017edbed688190baa61cbae5110c8e |
completed | May 11, 2026, 7:01 a.m. |
| PDg | Predicate description generation | batch_6a01839a63a48190a59a6c4464db0eea |
completed | May 11, 2026, 7:22 a.m. |
Created at: May 3, 2026, 4 p.m.