Triple
T33344521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republic of Zubrowka |
E853758
|
entity |
| Predicate | hasFictionalRailway |
P125068
|
FINISHED |
| Object | Zubrowkan railway system |
—
|
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: Zubrowkan railway system | Statement: [Republic of Zubrowka, hasFictionalRailway, Zubrowkan railway system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalRailway Context triple: [Republic of Zubrowka, hasFictionalRailway, Zubrowkan railway system]
-
A.
hasFictionalTransportLink
chosen
Indicates that there is a transportation connection between entities that exists only in a fictional or imagined context.
-
B.
hasFictionalUndergroundStation
Indicates that an entity features or includes a subway/metro station that exists only in fiction rather than in the real world.
-
C.
hasFictionalTubeStation
Indicates that an entity features or is associated with a tube (subway) station that exists only in fiction rather than in reality.
-
D.
inspiredFictionalRailway
Indicates that a real-world railway served as the creative basis or model for a fictional railway.
-
E.
hasRailSystem
Indicates that an entity possesses or is served by a rail-based transportation system.
- 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_69ff1e3e13c08190bb8990c44716b746 |
completed | May 9, 2026, 11:45 a.m. |
| PD | Predicate disambiguation | batch_69ff1dfcaf2c8190aaf2b428d57b7782 |
completed | May 9, 2026, 11:43 a.m. |
Created at: May 1, 2026, 1:34 a.m.