Triple
T32682066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wohratal |
E835611
|
entity |
| Predicate | isInLandkreis |
P77366
|
FINISHED |
| Object | Marburg-Biedenkopf |
—
|
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: Marburg-Biedenkopf | Statement: [Wohratal, isInLandkreis, Marburg-Biedenkopf]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInLandkreis Context triple: [Wohratal, isInLandkreis, Marburg-Biedenkopf]
-
A.
hasLandkreis
chosen
Indicates that an entity is associated with, or belongs to, a specific administrative district (Landkreis).
-
B.
isInMunicipality
Indicates that one entity (typically a place or address) is located within the administrative boundaries of a specific municipality.
-
C.
isInCadastralCounty
Indicates that one entity is located within, and administratively belongs to, a specific cadastral county used for land and property registration.
-
D.
isInCountySeatOf
Indicates that one entity is located within the town or city that serves as the administrative center (county seat) of a specified county.
-
E.
isRuralDistrictOf
Indicates that one administrative area is a rural district that belongs to or is governed as part of another, typically larger, administrative unit.
- 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_69f3493211388190993801216afbc2a7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c7e92f38819084db3081ae5de9ec |
completed | May 3, 2026, 3:58 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f617c08190a70ba880210f908c |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:09 a.m.