Triple
T27494769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TZ |
E693993
|
entity |
| Predicate | denotesCountryWithOfficialLanguage |
P95654
|
FINISHED |
| Object | Swahili |
—
|
NE NERFINISHED |
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: Swahili | Statement: [TZ, denotesCountryWithOfficialLanguage, Swahili]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: denotesCountryWithOfficialLanguage Context triple: [TZ, denotesCountryWithOfficialLanguage, Swahili]
-
A.
hasLanguageOfficial
Indicates that a language holds official status within a given entity, such as a country, region, or organization.
-
B.
hasCountryOfficialLanguageForm
Indicates that a country uses a specific official language in a particular written or standardized form.
-
C.
hasLanguageOfOfficialName
Indicates that an entity’s official name is expressed in a specified language.
-
D.
hasOfficialCountryLanguage
chosen
Indicates that a country recognizes a particular language as one of its official languages for governmental or legal purposes.
-
E.
usesOfficialLanguageOf
Indicates that one entity adopts and employs the official language of another entity for communication or formal purposes.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6359e3d3c81909814e2f0a7fb0ea9 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f631871c888190bf29466fe4254e51 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 1:07 p.m.