Triple
T22197892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Turkic scripts |
E548593
|
entity |
| Predicate | scriptFamilyIncludes |
P77267
|
FINISHED |
| Object | Arabic script |
—
|
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 script | Statement: [Turkic scripts, scriptFamilyIncludes, Arabic script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptFamilyIncludes Context triple: [Turkic scripts, scriptFamilyIncludes, Arabic script]
-
A.
scriptFamily
Indicates that one writing system belongs to the same broader script group or classification as another.
-
B.
scriptFamilyStatus
chosen
Indicates the familial or relational status between scripts, such as whether one script is derived from, related to, or grouped with another within a script family.
-
C.
syntaxFamily
Indicates that two linguistic elements share a common syntactic type, pattern, or structural classification within a grammar system.
-
D.
frameworkFamily
Indicates that one framework belongs to the same overarching family or lineage as another framework, typically sharing core principles, architecture, or origin.
-
E.
scriptFeature
Indicates that a script includes, supports, or is characterized by a particular feature or capability.
- 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_69e11e3ecc7c8190b5f94cd8f42e9d37 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12ae8c74c819080c7f9e8383ecaa7 |
completed | April 28, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69e71b48576c8190a8e93738fd9cfda5 |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:36 p.m.