Triple
T26614197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Awjila |
E668011
|
entity |
| Predicate | hasCaseSystemType |
P23828
|
FINISHED |
| Object | reduced case marking |
—
|
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: reduced case marking | Statement: [Awjila, hasCaseSystemType, reduced case marking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCaseSystemType Context triple: [Awjila, hasCaseSystemType, reduced case marking]
-
A.
hasTypeOfCase
Indicates that an entity is associated with or classified under a particular type or category of case.
-
B.
hasTypeSystem
Indicates that an entity employs, is governed by, or is associated with a particular type system (a defined set of rules for classifying and constraining types).
-
C.
hasCase
Indicates that one entity is involved in, associated with, or characterized by a particular case, instance, or occurrence represented by another entity.
-
D.
usesCaseSystem
chosen
Indicates that one entity employs or operates using a particular case system (e.g., grammatical or structural case-marking system).
-
E.
hasLegalSystemType
Indicates that an entity possesses or is governed by a particular type or form of legal system.
- 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_69ee9cfe16088190a3dddd68e3c7b1ea |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 27, 2026, 2:18 a.m.