Triple
T176507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marathi language |
E3586
|
entity |
| Predicate | usesScriptFeature |
P3097
|
FINISHED |
| Object | inherent vowel /ə/ |
—
|
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: inherent vowel /ə/ | Statement: [Marathi language, usesScriptFeature, inherent vowel /ə/]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesScriptFeature Context triple: [Marathi language, usesScriptFeature, inherent vowel /ə/]
-
A.
hasFeature
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
B.
supportsFeature
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
C.
hasSupported
Indicates that one entity has provided assistance, endorsement, or backing to another entity, either materially, emotionally, or through advocacy.
-
D.
usesStandard
Indicates that one entity adopts, follows, or operates according to a specified standard defined by another entity or reference.
-
E.
usesElement
chosen
Indicates that one entity makes use of, incorporates, or depends on a specified element in its structure, function, 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_69a25374990081909766d30c79a18e0e |
completed | Feb. 28, 2026, 2:31 a.m. |
| NER | Named-entity recognition | batch_69a258fd278481908ad4498e03f38e2f |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25669d99481908c5e82ba8641205a |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:39 a.m.