Triple
T29905138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Togolese Ministry of Education |
E759513
|
entity |
| Predicate | usesLanguageInPolicy |
P54671
|
FINISHED |
| Object | French |
—
|
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: French | Statement: [Togolese Ministry of Education, usesLanguageInPolicy, French]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesLanguageInPolicy Context triple: [Togolese Ministry of Education, usesLanguageInPolicy, French]
-
A.
usesLanguageFor
Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
-
B.
usesLanguageAs
Indicates that one entity communicates or operates using another entity as its language or linguistic medium.
-
C.
hasLanguagePolicyLink
Indicates that there is a specific URL or reference link associated with an entity that points to its language policy.
-
D.
hasLanguagePolicyContext
chosen
Indicates that there is an associated language-related policy, rule, or regulatory context governing how language is used or managed in relation to the subject.
-
E.
languagePolicyType
Indicates the specific category or type of language policy that governs how languages are used, managed, or regulated in a given context.
- 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_69f224600590819085e148a01c056ef6 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 29, 2026, 6:08 p.m.