Triple
T19732767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maniema Province |
E473894
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object | Songye |
—
|
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: Songye | Statement: [Maniema Province, hasEthnicGroup, Songye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Songye Context triple: [Maniema Province, hasEthnicGroup, Songye]
-
A.
Songye
chosen
Songye is a Bantu language spoken primarily by the Songye people in the Democratic Republic of the Congo.
-
B.
Karume
Karume is a Swahili surname most prominently associated with Abeid Karume, the first president of Zanzibar and a key figure in Tanzanian political history.
-
C.
Shundi
Shundi is a fictional kingdom from Satyajit Ray’s Bengali fantasy film and stories featuring Goopy and Bagha, known for its whimsical, magical setting.
-
D.
Shundi
Shundi is the posthumous temple name of Toghon Temür, the last emperor of China’s Yuan dynasty.
-
E.
Sihamoni
Sihamoni is the given name of Norodom Sihamoni, the current King of Cambodia and a member of the Cambodian royal family.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e651596b98819090bcaf05c7b74555 |
completed | April 20, 2026, 4:16 p.m. |
Created at: April 10, 2026, 1:47 p.m.