Triple
T34906006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DE-ST |
E1006726
|
entity |
| Predicate | hasSubdivisionNameLocal |
P46025
|
FINISHED |
| Object | Sachsen-Anhalt |
—
|
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: Sachsen-Anhalt | Statement: [DE-ST, hasSubdivisionNameLocal, Sachsen-Anhalt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubdivisionNameLocal Context triple: [DE-ST, hasSubdivisionNameLocal, Sachsen-Anhalt]
-
A.
hasSubdivisionName3
Indicates that an entity has a third-level subdivision whose name is given by the associated value.
-
B.
subdivisionNameLocal
chosen
Indicates the locally used or native-language name assigned to a specific administrative or geographic subdivision.
-
C.
hasSubdivisionLabel
Indicates that an entity assigns a specific label or name to one of its subdivisions or component parts.
-
D.
subdivisionNameLanguage
Indicates the language in which the name of a subdivision (such as a region, district, or administrative unit) is expressed.
-
E.
hasSubdivisionNameLevel1
Indicates that an entity has a first-level subdivision (e.g., state, province, region) identified by a specific name.
- 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_69f76dc1b4a081909b4c6e4d8ec0aa2d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ffac35ac5481908b6bdfd5bbe8c76e |
completed | May 9, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69ffabbfd2548190964c851496bbbaee |
completed | May 9, 2026, 9:48 p.m. |
Created at: May 3, 2026, 4 p.m.