Triple
T17215516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Celan |
E417841
|
entity |
| Predicate | workedAsTranslatorFromLanguage |
P71670
|
FINISHED |
| Object | Russian |
—
|
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: Russian | Statement: [Paul Celan, workedAsTranslatorFromLanguage, Russian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedAsTranslatorFromLanguage Context triple: [Paul Celan, workedAsTranslatorFromLanguage, Russian]
-
A.
workTranslatedFrom
Indicates that a work is a translation derived from an original work in another language.
-
B.
hasWorkTranslatedInto
Indicates that a work has been translated into a specified language or target work.
-
C.
hasWorkedInLanguage
Indicates that an entity has performed work or professional activities using a particular language.
-
D.
languageTranslatedFrom
chosen
Indicates that a language is the source/original language from which content has been translated into another language.
-
E.
laterTranslatedAs
Indicates that something was translated at a later time into a different language, form, or version under a specified title or expression.
- 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dc9f96881909eb86786a76e17e4 |
completed | April 19, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69e3831e354881908c5505ffd15c84e9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:38 a.m.