Triple
T37650735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rondo Daszyńskiego |
E937164
|
entity |
| Predicate | connectsWithRoad |
P11435
|
FINISHED |
| Object | Prosta Street |
—
|
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: Prosta Street | Statement: [Rondo Daszyńskiego, connectsWithRoad, Prosta Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsWithRoad Context triple: [Rondo Daszyńskiego, connectsWithRoad, Prosta Street]
-
A.
connectsRoadNetwork
Indicates that one entity is linked to another as part of the same road network, enabling continuous vehicular or transport connectivity between them.
-
B.
linkedByRoadTo
chosen
Indicates that two locations are directly connected to each other by a road suitable for travel.
-
C.
hasConnectingRoadNumber
Indicates that there exists a road connection between two locations or road segments identified by a specific road number.
-
D.
hasRoadConnectionRegion
Indicates that there is a road-based transportation link connecting one region to another.
-
E.
hasConnectingStreet
Indicates that two locations are linked by a street that directly connects them.
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fff86e544c81908063f61b876c9d78 |
completed | May 10, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69fff7e7cb688190977eeca41aad25b9 |
completed | May 10, 2026, 3:13 a.m. |
Created at: May 3, 2026, 4:18 p.m.