Triple
T20846344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ajka District |
E513234
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Uzsa |
—
|
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: Uzsa | Statement: [Ajka District, containsSettlement, Uzsa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uzsa Context triple: [Ajka District, containsSettlement, Uzsa]
-
A.
Uzsa
chosen
Uzsa is a small village in Veszprém County in western Hungary.
-
B.
Uzda
Uzda is a small town in present-day Belarus, historically home to a significant Jewish community.
-
C.
Uzyn
Uzyn is a small town in central Ukraine known for its agricultural surroundings and proximity to the regional center of Bila Tserkva.
-
D.
Uzeste
Uzeste is a small commune in southwestern France notable for its historic church that houses the tomb of Pope Clement V.
-
E.
Uz
Uz is a minor biblical figure mentioned in the Book of Genesis as one of the early descendants in Abraham’s extended family line.
- 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c34ffb588190881953a0480b29a8 |
completed | April 21, 2026, 12:22 a.m. |
Created at: April 16, 2026, 12:43 p.m.