Triple
T33344522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republic of Zubrowka |
E853758
|
entity |
| Predicate | hasFictionalSpaTown |
P19664
|
FINISHED |
| Object | Nebelsbad spa resort |
—
|
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: Nebelsbad spa resort | Statement: [Republic of Zubrowka, hasFictionalSpaTown, Nebelsbad spa resort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalSpaTown Context triple: [Republic of Zubrowka, hasFictionalSpaTown, Nebelsbad spa resort]
-
A.
hasFictionalNearbyTown
Indicates that an entity is associated with a fictional town located in its vicinity or surrounding area.
-
B.
hasFictionalTownType
Indicates that a fictional town is classified as being of a particular type or category.
-
C.
hasFictionalTownBasedOn
Indicates that a fictional town is modeled on, inspired by, or derived from a specific real-world town or location.
-
D.
hasSpaTown
chosen
Indicates that a place is associated with or contains a town known for its spa or therapeutic bathing facilities.
-
E.
hasFictionalCountySeatRole
Indicates that an entity serves in the role of county seat within a fictional or imaginary administrative setting.
- F. None of above.
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_69f3496a1a588190bad9cbe9221144e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff1f3f94fc819095955299f50ab4ce |
completed | May 9, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69ff1ea47748819082f63d9b9d9c3e65 |
completed | May 9, 2026, 11:46 a.m. |
Created at: May 1, 2026, 1:34 a.m.