Triple
T37393188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lüttringhauser Straße area |
E928773
|
entity |
| Predicate | roadCategoryOfLüttringhauserStraße |
P1019
|
FINISHED |
| Object | city street |
—
|
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: city street | Statement: [Lüttringhauser Straße area, roadCategoryOfLüttringhauserStraße, city street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadCategoryOfLüttringhauserStraße Context triple: [Lüttringhauser Straße area, roadCategoryOfLüttringhauserStraße, city street]
-
A.
roadType
chosen
Indicates the classification or category of a road based on its functional or physical characteristics.
-
B.
roadTypeToRegion
Indicates the association between a specific type of road and the geographic region in which that road type applies or is found.
-
C.
roadTypeAtSquare
Indicates the specific type or classification of road present at a given square or location in a spatial grid or map.
-
D.
roadFeature
Indicates that an entity is a specific physical or functional characteristic associated with a road, such as its structure, markings, or related infrastructure.
-
E.
isSideStreetOf
Indicates that one street is a smaller, less prominent road that connects to or branches off from another main street.
- 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_69f76ebb10c481909b54b9dba263e29f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.