Triple
T31356016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess in Bavaria |
E799732
|
entity |
| Predicate | originalGermanForm |
P22792
|
FINISHED |
| Object | Herzogin in Bayern |
—
|
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: Herzogin in Bayern | Statement: [Duchess in Bavaria, originalGermanForm, Herzogin in Bayern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalGermanForm Context triple: [Duchess in Bavaria, originalGermanForm, Herzogin in Bayern]
-
A.
pluralGermanName
Indicates that the given name is the correct German plural form of a singular term.
-
B.
abbreviationGerman
Indicates that one term is the German-language abbreviation or shortened form of another term.
-
C.
nameInGerman
chosen
Indicates that an entity is known or referred to by a specific name in the German language.
-
D.
germanPart
Indicates that one entity is a component, section, or segment that belongs to or forms part of something specifically in a German context (e.g., language, jurisdiction, or origin).
-
E.
ethnicallyGermanizedBy
Indicates that an entity has adopted or been assimilated into German ethnic identity, culture, or characteristics as a result of influence or actions by another entity.
- 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_69f224e5e9bc8190a16339328897c4f8 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a00b479c1588190af6e0698b7f8d7f7 |
completed | May 10, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_6a00b4158260819087d0cfad8b18cef4 |
completed | May 10, 2026, 4:36 p.m. |
Created at: April 29, 2026, 9:17 p.m.