Triple
T20026473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Little Carpathians wine region |
E494994
|
entity |
| Predicate | includesTown |
P847
|
FINISHED |
| Object | Modra |
E494992
|
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: Modra | Statement: [Little Carpathians wine region, includesTown, Modra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Modra Context triple: [Little Carpathians wine region, includesTown, Modra]
-
A.
Modra
chosen
Modra is a historic Slovak town in the foothills of the Little Carpathians, renowned for its wine production and traditional ceramics.
-
B.
Krasna
Krasna is a surname most notably associated with American screenwriter, playwright, and film producer Norman Krasna.
-
C.
Mumlava
Mumlava is a river in the Krkonoše (Giant) Mountains of the Czech Republic, known for its scenic waterfalls and gorges near the town of Harrachov.
-
D.
Vydra
Vydra is a river in the Šumava region of the Czech Republic, known for its rocky riverbed, scenic gorges, and role as one of the headwaters of the Otava River.
-
E.
Lučina
Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6628e1eec81908e4c9b2b0b68f0e4 |
completed | April 20, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a080e2f549c8190b04f8470fbb63a0c |
completed | May 16, 2026, 6:26 a.m. |
Created at: April 11, 2026, 3:35 p.m.