Triple
T135581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swahili language |
E2738
|
entity |
| Predicate | historicallyWrittenIn |
P4037
|
FINISHED |
| Object | Arabic script |
—
|
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 script | Statement: [Swahili language, historicallyWrittenIn, Arabic script]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicallyWrittenIn Context triple: [Swahili language, historicallyWrittenIn, Arabic script]
-
A.
hasWritingTraditionSince
Indicates that a writing tradition has been present or established for an entity starting from a specified point in time.
-
B.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
C.
historicalScript
chosen
Indicates that an entity is or was written in, or otherwise associated with, a particular historical writing system or script.
-
D.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
E.
historicallyBorneBy
Indicates that an entity has carried, possessed, or used another entity (such as a name, title, or symbol) at some point in the past.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257a3ad908190b6a8652f09ae0cbb |
completed | Feb. 28, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69a25651b9048190a6277b7fec98c1ea |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.