Triple
T5189217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumyk |
E117107
|
entity |
| Predicate | scriptChange |
P32645
|
FINISHED |
| Object | Arabic to Latin in early 20th century |
—
|
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: Arabic to Latin in early 20th century | Statement: [Kumyk, scriptChange, Arabic to Latin in early 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptChange Context triple: [Kumyk, scriptChange, Arabic to Latin in early 20th century]
-
A.
scriptChangePolicy
Indicates a policy governing when, how, or under what conditions a script may be modified or updated.
-
B.
scriptCode
Indicates that an entity is associated with a particular writing system or script, identified by a standardized script code.
-
C.
scriptEvolution
chosen
Indicates how a script or written system changes, develops, or transforms over time in relation to its earlier or later forms.
-
D.
scriptEditor
Indicates that an entity serves as the editor or editing environment used to create or modify a script.
-
E.
script
Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
- 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_69bd44620ff48190bcac01782107a397 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79c732b48190af62dfffcbc5e3a6 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b7e8b4819092ec3965e11f2dea |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:46 p.m.