Triple
T23721100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karlino |
E586143
|
entity |
| Predicate | formerGermanName |
P22792
|
FINISHED |
| Object | Körlin an der Persante |
—
|
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: Körlin an der Persante | Statement: [Karlino, formerGermanName, Körlin an der Persante]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerGermanName Context triple: [Karlino, formerGermanName, Körlin an der Persante]
-
A.
nameInGerman
chosen
Indicates that an entity is known or referred to by a specific name in the German language.
-
B.
countryDuringGermanRule
Indicates that one entity functioned as a country or territorial unit during a period when it was under German rule or control.
-
C.
GermanNameOfCapital
Indicates that the given name is the German-language name of a specified capital city.
-
D.
wasUnderGermanRuleAtBirthOf
Indicates that the subject’s place of birth was under German political or administrative control at the time of the object’s birth.
-
E.
predecessorAsKingOfGermany
Indicates that one entity served as the immediately preceding king of Germany to the other 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_69e24906fb108190a6898751e46bdc11 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b910759c8190be189db3e86d7258 |
completed | April 29, 2026, 7:53 a.m. |
| PD | Predicate disambiguation | batch_69f155e4b1148190836ede4741dcb888 |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 7:01 p.m.