Triple
T4058168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spiš Castle |
E84743
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Levoča |
E413550
|
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: Levoča | Statement: [Spiš Castle, nearbyCity, Levoča]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Levoča Context triple: [Spiš Castle, nearbyCity, Levoča]
-
A.
Levoča
chosen
Levoča is a historic town in eastern Slovakia renowned for its well-preserved medieval center and Gothic architecture, including the Church of St. James with its famous wooden altar by Master Paul.
-
B.
Trebišov
Trebišov is a town in eastern Slovakia known as an administrative and cultural center of the Trebišov District.
-
C.
Prešporok
Prešporok is the historical Slovak name for the city now known as Bratislava, the capital of Slovakia.
-
D.
Liptovská Osada
Liptovská Osada is a village in the Liptov region of northern Slovakia, known for its mountainous surroundings and proximity to the Low Tatras.
-
E.
Dunajská Streda
Dunajská Streda is a town in southern Slovakia known as a cultural and economic center of the Hungarian minority in the country.
- 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_69aed933bec881909edfa28ebb69c634 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefbaefcb081908aab3963dcd61a20 |
completed | March 9, 2026, 4:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b67b9e1b4081909f53466a603d7061 |
completed | March 15, 2026, 9:27 a.m. |
Created at: March 9, 2026, 3:38 p.m.