Triple
T33363970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermsdorfer Kreuz |
E854299
|
entity |
| Predicate | roadA9Direction |
P76663
|
FINISHED |
| Object | northbound towards Berlin |
—
|
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: northbound towards Berlin | Statement: [Hermsdorfer Kreuz, roadA9Direction, northbound towards Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadA9Direction Context triple: [Hermsdorfer Kreuz, roadA9Direction, northbound towards Berlin]
-
A.
roadAxis
Indicates a central reference line that defines the primary longitudinal direction or alignment of a road.
-
B.
routeDirectionA
chosen
Indicates the primary or first directional orientation or heading associated with a specific route.
-
C.
arterialRoad
Indicates that a road functions as a primary high-capacity route that channels major traffic flows between different areas of a transport network.
-
D.
roadType
Indicates the classification or category of a road based on its functional or physical characteristics.
-
E.
roadFeature
Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
- 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_69f3496bda8c8190bfc8fade9d1b791c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f38159d08190980ad639e08f00f4 |
completed | May 3, 2026, 7:04 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d7bee48190b94e0beb48a1d7fa |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:34 a.m.