Triple
T37367469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Preis der Leipziger Buchmesse |
E927749
|
entity |
| Predicate | hasTranslationCategory |
P2303
|
FINISHED |
| Object | translation into German |
—
|
LITERAL FINISHED |
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: translation into German | Statement: [Preis der Leipziger Buchmesse, hasTranslationCategory, translation into German]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTranslationCategory Context triple: [Preis der Leipziger Buchmesse, hasTranslationCategory, translation into German]
-
A.
hasTranslation
chosen
Indicates that one entity is a translation or translated version of another entity in a different language.
-
B.
hasTranslationComponent
Indicates that one entity includes or is associated with a component responsible for translating or converting content from one form or language to another.
-
C.
hasTranslationEquivalent
Indicates that one expression in a given language corresponds in meaning to another expression in a different language.
-
D.
hasTranslationBase
Indicates that one entity serves as the original source or base text from which the other entity is translated.
-
E.
hasTranslationPlatform
Indicates that one entity provides or is associated with a platform used to perform or manage translations for 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_69f76eb820248190a5c395ca50ad002a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a00233e2170819084bee0c8f74cc1a4 |
completed | May 10, 2026, 6:18 a.m. |
| PD | Predicate disambiguation | batch_6a0022943fd08190b73007f080d5971d |
completed | May 10, 2026, 6:15 a.m. |
Created at: May 3, 2026, 4:16 p.m.