Triple
T23883528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lezgin |
E600269
|
entity |
| Predicate | hasCurrentScript |
P2936
|
FINISHED |
| Object | Cyrillic script |
—
|
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: Cyrillic script | Statement: [Lezgin, hasCurrentScript, Cyrillic script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCurrentScript Context triple: [Lezgin, hasCurrentScript, Cyrillic script]
-
A.
hasScriptStatus
Indicates that an entity has a particular script-related state or condition, such as whether a script is present, active, or in a given status.
-
B.
containsScript
Indicates that one entity includes or embeds the script of another entity within it.
-
C.
hasScriptCode
Indicates that an entity is associated with a particular writing system identified by a specific script code.
-
D.
hasScriptRegulator
Indicates that an entity has an associated mechanism or component that controls or governs its script or scripting behavior.
-
E.
hasCurrent
chosen
Indicates that an entity presently possesses, exhibits, or is associated with a particular state, attribute, or resource at the current time.
- 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_69e295318e148190b9979d8fc02e168f |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ccfbbe4c819093e590709719ab72 |
completed | April 29, 2026, 9:18 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:24 p.m.