Triple
T7401918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNOG |
E170768
|
entity |
| Predicate | languageService |
P11734
|
FINISHED |
| Object | Arabic |
—
|
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: Arabic | Statement: [UNOG, languageService, Arabic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageService Context triple: [UNOG, languageService, Arabic]
-
A.
languageFeature
Indicates that one entity is a characteristic, property, or capability of a language associated with the other entity.
-
B.
languageProvision
chosen
Indicates that one entity supplies, supports, or makes available a particular language (or set of languages) for use by another entity.
-
C.
languageOfCode
Indicates that a programming code artifact is written in, or uses, a particular programming language.
-
D.
supportsLanguageVersion
Indicates that one entity provides compatibility with, or can correctly operate using, a specified version of a language.
-
E.
languageAssociation
Indicates an association or relationship between entities based on a language they use, represent, or are linked to.
- 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_69c68a5f04188190ac266569c9280347 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f26d6d6081909c7272a9ccae0d97 |
completed | March 27, 2026, 9:11 p.m. |
| PD | Predicate disambiguation | batch_69c6f0323b2c819098ab72c33e6d8534 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:10 p.m.