Triple
T16567897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandara language |
E402508
|
entity |
| Predicate | isLinguisticallyDescribedIn |
P43659
|
FINISHED |
| Object | Chadic language surveys |
—
|
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: Chadic language surveys | Statement: [Mandara language, isLinguisticallyDescribedIn, Chadic language surveys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLinguisticallyDescribedIn Context triple: [Mandara language, isLinguisticallyDescribedIn, Chadic language surveys]
-
A.
hasLinguisticDescriptionBy
Indicates that something is described or characterized using language by a particular source, agent, or medium.
-
B.
isLanguageOf
Indicates that a particular language is used as the official or primary language associated with a given entity (such as a person, document, or region).
-
C.
hasLinguisticDocumentation
chosen
Indicates that there exists recorded linguistic information or documentation about the language or linguistic properties of the subject.
-
D.
hasLanguageRepresentation
Indicates that an entity is expressed, encoded, or represented using a particular natural or formal language.
-
E.
languageOfOriginalDescription
Indicates that something is expressed or documented in its initial or source language version.
- 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_69d8838648088190acf97ef11fc3f61b |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35772f6608190a125c7d3c199c3e2 |
completed | April 18, 2026, 10:05 a.m. |
| PD | Predicate disambiguation | batch_69e296a47b7481909d9958158510c806 |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:16 a.m.