Triple
T13846408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hron River |
E332816
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Žiar nad Hronom |
E300712
|
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: Žiar nad Hronom | Statement: [Hron River, flowsThrough, Žiar nad Hronom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Žiar nad Hronom Context triple: [Hron River, flowsThrough, Žiar nad Hronom]
-
A.
Žiar nad Hronom
chosen
Žiar nad Hronom is an industrial town in central Slovakia known for its aluminum production and location along the Hron River.
-
B.
Čierna nad Tisou
Čierna nad Tisou is a small town in eastern Slovakia known as an important railway and border-crossing hub with Ukraine.
-
C.
Na Příkopě
Na Příkopě is one of Prague’s main commercial and shopping streets, known for its upscale stores and central location between Wenceslas Square and the Old Town.
-
D.
Lady of Mělník
Lady of Mělník was a noble title associated with the Bohemian estates, notably borne by Queen Barbara of Cilli as part of her extensive landholdings and influence in the Kingdom of Bohemia.
-
E.
Loučka
Loučka is a river in the Czech Republic that serves as a left-bank tributary of the Svratka River.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02b1a25c8190a9f85ba43c421188 |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c0ef9e7c8190b96c2b83d04708e1 |
completed | May 3, 2026, 9:41 p.m. |
Created at: April 9, 2026, 10:13 p.m.