Triple
T12384654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanzania and Zambia |
E295831
|
entity |
| Predicate | shareRegionalLanguage |
P33593
|
FINISHED |
| Object | Swahili (in some border areas) |
—
|
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: Swahili (in some border areas) | Statement: [Tanzania and Zambia, shareRegionalLanguage, Swahili (in some border areas)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareRegionalLanguage Context triple: [Tanzania and Zambia, shareRegionalLanguage, Swahili (in some border areas)]
-
A.
regionLanguage
Indicates that a particular language is used or officially recognized within a specific geographic region.
-
B.
sharesLanguageWith
chosen
Indicates that two entities use at least one common language for communication.
-
C.
recognizedRegionalLanguage
Indicates that a language holds officially recognized status within a specific region or subnational jurisdiction.
-
D.
alsoInLanguageRegion
Indicates that two or more entities are located within or associated with the same language-defined geographic region.
-
E.
regionOfMajorLanguage
Indicates the geographic region where a particular language is predominantly spoken or holds major usage.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbc3f608190b0ee3c4f304a94db |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.