Triple
T12506547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mureș County |
E298961
|
entity |
| Predicate | containsResort |
P25904
|
FINISHED |
| Object | Sovata |
E986767
|
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: Sovata | Statement: [Mureș County, containsResort, Sovata]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sovata Context triple: [Mureș County, containsResort, Sovata]
-
A.
Sovata
chosen
Sovata is a Romanian spa town in central Transylvania, renowned for its heliothermal salt lakes and therapeutic resorts.
-
B.
Sovana
Sovana is a small medieval village in southern Tuscany, Italy, renowned for its well-preserved historic center and nearby Etruscan archaeological sites.
-
C.
Sosva
Sosva is a rural locality in Sverdlovsk Oblast, Russia, historically known as the site of a Soviet-era labor camp where Finnish communist leader Kullervo Manner died.
-
D.
Sovern
Sovern is a surname most notably associated with Michael I. Sovern, an American legal scholar and former president of Columbia University.
-
E.
Sochalien
Sochalien is the French demonym for an inhabitant or native of the town of Sochaux in eastern France.
- 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_69d6ada4cd388190ae3bbf83ff87057a |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94dfddf38819099263b8b1e804736 |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6557243788190854208113600324e |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 8, 2026, 9:57 p.m.