Triple
T1401712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shilha |
E31598
|
entity |
| Predicate | hasStatusInMorocco |
P15010
|
FINISHED |
| Object | official Amazigh language (as part of Tamazight) |
—
|
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: official Amazigh language (as part of Tamazight) | Statement: [Shilha, hasStatusInMorocco, official Amazigh language (as part of Tamazight) ]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStatusInMorocco Context triple: [Shilha, hasStatusInMorocco, official Amazigh language (as part of Tamazight) ]
-
A.
statusInEgypt
Indicates the legal, social, or official condition or standing that an entity holds specifically within the context of Egypt.
-
B.
deFactoStatus
Indicates that one entity holds a role, position, or status in practice or by custom, even if it is not formally or legally recognized.
-
C.
hasStatusIn
chosen
Indicates that an entity holds or is assigned a particular status within a specified context, scope, or system.
-
D.
statusInIran
Indicates the legal, social, or political standing or condition of an entity specifically within the context of Iran.
-
E.
statusInUnitedStates
Indicates the legal or official standing that an entity holds within the jurisdiction of the United States.
- 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_69a49918e1f88190ba610f9dc8114578 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c39da20c8190b9c82cc4ad747c66 |
completed | March 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.