Triple
T18682167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ajka |
E456759
|
entity |
| Predicate | hasRailConnectionTo |
P848
|
FINISHED |
| Object | Szombathely |
—
|
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: Szombathely | Statement: [Ajka, hasRailConnectionTo, Szombathely]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Szombathely Context triple: [Ajka, hasRailConnectionTo, Szombathely]
-
A.
Szombathely
chosen
Szombathely is one of Hungary’s oldest cities, known for its Roman heritage and role as a regional cultural and economic center near the Austrian border.
-
B.
Sátoraljaújhely
Sátoraljaújhely is a historic town in northeastern Hungary near the Slovak border, known for its wine region, cultural heritage, and scenic Zemplén Mountains setting.
-
C.
Szekszárd
Szekszárd is a historic Hungarian town renowned as one of the country’s leading red wine regions and the administrative center of Tolna County.
-
D.
Kalocsa
Kalocsa is a historic town in southern Hungary known as an important Roman Catholic archiepiscopal center and for its traditional paprika production and folk art.
-
E.
Szatmárnémeti
Szatmárnémeti is the Hungarian name for Satu Mare, a major city in northwestern Romania near the Hungarian and Ukrainian borders.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55b2906ec8190ad8db8e3ae6b2945 |
completed | April 19, 2026, 10:46 p.m. |
Created at: April 10, 2026, 11:49 a.m.