Triple
T18610651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shteynberg |
E454881
|
entity |
| Predicate | hasTransliterationPattern |
P78931
|
FINISHED |
| Object | Steinberg → Shteynberg |
—
|
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: Steinberg → Shteynberg | Statement: [Shteynberg, hasTransliterationPattern, Steinberg → Shteynberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTransliterationPattern Context triple: [Shteynberg, hasTransliterationPattern, Steinberg → Shteynberg]
-
A.
hasTransliterationRule
chosen
Indicates that there exists a specific rule or mapping that defines how text in one script or writing system is systematically converted into another.
-
B.
hasTransliterationType
Indicates the type or system of transliteration used to convert text from one writing system into another.
-
C.
hasTransliterationRole
Indicates that an entity participates in a transliteration process with a specific role (e.g., source, target, or agent of transliteration).
-
D.
transliterationName
Indicates that one entity is the transliterated form of another entity’s name from one writing system into another.
-
E.
isTransliteratedWithoutDiacriticsInEnglish
Indicates that an entity’s name or term is represented in English letters without including any diacritical marks from the original script.
- 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54d013748819099126e27e7ec543d |
completed | April 19, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69e478cf5e888190a0b1074b0c6525df |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:45 a.m.