Triple
T19364970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Bulgaria |
E484377
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Aytos |
—
|
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: Aytos | Statement: [Southern Bulgaria, hasMajorCity, Aytos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aytos Context triple: [Southern Bulgaria, hasMajorCity, Aytos]
-
A.
Aytos
chosen
Aytos is a small town in southeastern Bulgaria known as an administrative and economic center within Burgas Province.
-
B.
Ahtena
Ahtena is an Athabaskan-speaking Indigenous people of south-central Alaska, traditionally living around the Copper River basin.
-
C.
Atheras
Atheras is a mountainous region on the Greek island of Ikaria, known for its rugged terrain and scenic landscapes.
-
D.
Afytos
Afytos is a traditional seaside village in northern Greece known for its stone houses, scenic views over the Toroneos Gulf, and relaxed holiday atmosphere.
-
E.
Azotus
Azotus, the Greek name for the ancient Philistine city of Ashdod on the Mediterranean coast, was a significant biblical and historical port city in the region of modern-day Israel.
- 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.