Triple
T6668457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Standard Moroccan Amazigh |
E151663
|
entity |
| Predicate | hasSyntacticType |
P41847
|
FINISHED |
| Object | verb–subject–object dominant order |
—
|
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: verb–subject–object dominant order | Statement: [Standard Moroccan Amazigh, hasSyntacticType, verb–subject–object dominant order]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSyntacticType Context triple: [Standard Moroccan Amazigh, hasSyntacticType, verb–subject–object dominant order]
-
A.
syntacticType
chosen
Indicates the grammatical or structural category that characterizes how an expression functions within a syntactic construction.
-
B.
haveType
Indicates that an entity belongs to or is classified under a specified type or category.
-
C.
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).
-
D.
hasStructureType
Indicates that an entity possesses or is classified by a specific structural type or configuration.
-
E.
hasLanguageType
Indicates that an entity is associated with a particular type or category of language (e.g., spoken, written, programming, sign).
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ce738fe88190a5557900efeec7ec |
completed | March 27, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69c6ad09974c81908784300ae218961f |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:02 p.m.