Triple
T23409936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernst-Reuter-Platz |
E560037
|
entity |
| Predicate | roadTypeAtSquare |
P152151
|
FINISHED |
| Object | multi-lane arterial roads |
—
|
LITERAL 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: multi-lane arterial roads | Statement: [Ernst-Reuter-Platz, roadTypeAtSquare, multi-lane arterial roads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadTypeAtSquare Context triple: [Ernst-Reuter-Platz, roadTypeAtSquare, multi-lane arterial roads]
-
A.
roadType
Indicates the classification or category of a road based on its functional or physical characteristics.
-
B.
roadNumberType
Indicates the classification or type category assigned to a road’s identifying number (e.g., highway, route, local road).
-
C.
roadFeature
Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
-
D.
roadSystem
Indicates a relationship where multiple roads are organized and connected as part of a larger, integrated transportation network or infrastructure.
-
E.
roadPassType
Indicates the type or category of permission or authorization required to use or pass along a particular road or route.
- F. None of above. chosen
Provenance (4 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a510b3848190ae42679ef0bcd424 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f07cbbd7488190ab3c8ae7d0fb68bf |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 17, 2026, 5:38 p.m.