Triple
T11704124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Felvidék |
E278196
|
entity |
| Predicate | hasImportantMiningTown |
P14082
|
FINISHED |
| Object | Körmöcbánya |
E1043223
|
NE FINISHED |
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: Körmöcbánya | Statement: [Felvidék, hasImportantMiningTown, Körmöcbánya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Körmöcbánya Context triple: [Felvidék, hasImportantMiningTown, Körmöcbánya]
-
A.
Körmöcbánya
chosen
Körmöcbánya is a historic mining town in present-day Slovakia, renowned for its medieval gold and coin-minting traditions.
-
B.
Bonyhád
Bonyhád is a town in southern Hungary known as an important local center within Tolna County.
-
C.
Bodrogköz
Bodrogköz is a low-lying, marshy region in northeastern Hungary known for its riverine landscapes, wetlands, and traditional rural settlements.
-
D.
Körmend
Körmend is a small town in western Hungary, known for its historic castle and location near the Austrian border.
-
E.
Zólyom
Zólyom is the historical Hungarian name for the Slovak town of Zvolen, an important medieval center in central Slovakia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a49b1080819096593733ee48a187 |
completed | April 10, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76b9112948190a0dd747a67f8206a |
completed | May 3, 2026, 3:36 p.m. |
Created at: April 8, 2026, 9:40 p.m.