Triple
T35342923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Szászsebes |
E1020653
|
entity |
| Predicate | correspondsToGermanName |
P22792
|
FINISHED |
| Object | Mühlbach |
—
|
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: Mühlbach | Statement: [Szászsebes, correspondsToGermanName, Mühlbach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondsToGermanName Context triple: [Szászsebes, correspondsToGermanName, Mühlbach]
-
A.
correspondsToGermanAbbreviation
Indicates that one entity is the German-language abbreviation or acronym that corresponds to, or represents, the other entity.
-
B.
nameInGerman
chosen
Indicates that an entity is known or referred to by a specific name in the German language.
-
C.
equivalentSurnameInGerman
Indicates that two surnames are equivalent to each other when translated into or represented in the German language.
-
D.
correspondsToAbbreviationInGerman
Indicates that one entity is the full form or concept for which the other entity serves as the corresponding abbreviation in the German language.
-
E.
hasOfficialLanguageNameInGerman
Indicates that an entity has an official language name expressed specifically in the German language.
- 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_69f76debb4e08190be52d89b8af2392d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:03 p.m.