Triple
T35536539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moldavia |
E1026944
|
entity |
| Predicate | administrativeLanguageInfluence |
P106919
|
FINISHED |
| Object | Old Church Slavonic |
—
|
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: Old Church Slavonic | Statement: [Moldavia, administrativeLanguageInfluence, Old Church Slavonic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: administrativeLanguageInfluence Context triple: [Moldavia, administrativeLanguageInfluence, Old Church Slavonic]
-
A.
influencesLanguageOf
chosen
Indicates that one entity affects, shapes, or alters the language used by another entity.
-
B.
languageInfluence
Indicates that one language has an effect on the development, usage, or characteristics of another language.
-
C.
languageOfInfluence
Indicates a relationship where one language has influenced the development, usage, or characteristics of another language.
-
D.
linguisticInfluence
Indicates that one entity has affected, shaped, or contributed to the language, style, or linguistic features of another entity.
-
E.
influencedLanguage
Indicates that one language has had an effect on the development, structure, or usage of another 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_69f76dff7e508190b28ceeee770dce23 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fe163a41a0819098403b470e327d29 |
completed | May 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fe1358db5c819092570814a37ef5bd |
completed | May 8, 2026, 4:46 p.m. |
Created at: May 3, 2026, 4:04 p.m.