Triple
T8542119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | pula–thebe system |
E202221
|
entity |
| Predicate | subunitNameLanguage |
P47001
|
FINISHED |
| Object | Setswana |
—
|
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: Setswana | Statement: [pula–thebe system, subunitNameLanguage, Setswana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subunitNameLanguage Context triple: [pula–thebe system, subunitNameLanguage, Setswana]
-
A.
subdivisionNameLanguage
Indicates the language in which the name of a subdivision (such as a region, district, or administrative unit) is expressed.
-
B.
hasSubunitName
Indicates that an entity includes or is associated with a named subunit or component as part of its structure or organization.
-
C.
subunitNamePlural
Indicates that an entity has multiple subunits and specifies the pluralized name used to refer collectively to those subunits.
-
D.
subunitType
Indicates that one entity is a specific kind or classification of subunit within the structure or composition of another entity.
-
E.
componentNameLanguage
chosen
Indicates that a component’s name is expressed or recorded in a specific language.
- 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_69ca832461e88190a654c5e44e233aa8 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6e26be48190b10bc62fad178dad |
completed | March 31, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69cbd111bf988190be98c92a607c6456 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:18 p.m.