Triple
T19766714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | municipality of Eordaia |
E474776
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Komnina |
—
|
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: Komnina | Statement: [municipality of Eordaia, hasSettlement, Komnina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Komnina Context triple: [municipality of Eordaia, hasSettlement, Komnina]
-
A.
Komnina
chosen
Komnina is a village-level settlement located within the municipality of Eordaia in the Western Macedonia region of Greece.
-
B.
Kommunar
Kommunar is a small town in Leningrad Oblast, Russia, known for its location along the Izhora River southeast of Saint Petersburg.
-
C.
Komiža
Komiža is a small coastal town and fishing port on the western side of the Croatian island of Vis in the Adriatic Sea.
-
D.
Pomarance
Pomarance is a historic Tuscan town in central Italy, known for its medieval architecture and proximity to the geothermal area of Larderello.
-
E.
Kombe
Kombe is a Bantu language spoken by the Kombe people of coastal Equatorial Guinea and nearby regions, closely related to other Ndowe-area languages.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653232e508190a7d484c0a1e2939a |
completed | April 20, 2026, 4:24 p.m. |
Created at: April 10, 2026, 1:48 p.m.