Triple
T3683114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Südwestsachsen region |
E78156
|
entity |
| Predicate | hasCityType |
P749
|
FINISHED |
| Object | medium-sized cities |
—
|
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: medium-sized cities | Statement: [Südwestsachsen region, hasCityType, medium-sized cities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCityType Context triple: [Südwestsachsen region, hasCityType, medium-sized cities]
-
A.
hasComponentCity
Indicates that an entity includes or is composed of one or more cities as its constituent parts.
-
B.
isInCity
Indicates that one entity is located within the geographical boundaries of a specified city.
-
C.
hasMunicipalityType
Indicates that an administrative unit is classified as having a specific type or category of municipality (e.g., city, town, village).
-
D.
hasTargetCity
Indicates that something is directed toward, intended for, or specifically associated with a particular city as its target.
-
E.
urbanAreaType
chosen
Indicates the classification of an area based on its urban characteristics or development type (e.g., city, town, suburb, metropolitan region).
- 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_69ad85e18c1c8190be8aafb227f39f48 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc4948cc48190ab1f59cc4a2437cc |
completed | March 8, 2026, 6:48 p.m. |
| PD | Predicate disambiguation | batch_69adb84be1fc81909721c871babb4633 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:26 p.m.