Triple
T35811913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | სომხები |
E1035253
|
entity |
| Predicate | საუბრობენ ენაზე |
P34466
|
FINISHED |
| Object | სომხური ენა |
—
|
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: სომხური ენა | Statement: [სომხები, საუბრობენ ენაზე, სომხური ენა]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: საუბრობენ ენაზე Context triple: [სომხები, საუბრობენ ენაზე, სომხური ენა]
-
A.
speaksIn
chosen
Indicates that an entity uses or expresses itself in a particular language or medium when speaking.
-
B.
languageOfExpression
Indicates that a particular language is used as the medium or form in which an expression (such as a text, utterance, or work) is realized.
-
C.
isSpokenOn
Indicates that a particular language, phrase, or utterance is used or occurs during a specified time, event, or occasion.
-
D.
usesLanguageFor
Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
-
E.
usesLanguageAs
Indicates that one entity communicates or operates using another entity as its language or linguistic medium.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d219f8819081dc4ce3c83ca0cb |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.