Triple
T22322005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kenyah people |
E551808
|
entity |
| Predicate | subgroup |
P10
|
FINISHED |
| Object | Kenyah Uma Suling |
—
|
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: Kenyah Uma Suling | Statement: [Kenyah people, subgroup, Kenyah Uma Suling]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kenyah Uma Suling Context triple: [Kenyah people, subgroup, Kenyah Uma Suling]
-
A.
Sengkuni
Sengkuni is a cunning and manipulative character in Javanese adaptations of the Mahabharata, often portrayed as a scheming advisor who fuels conflict and deceit.
-
B.
Kenyah Uma’ Pawe
Kenyah Uma’ Pawe is a specific variety of the Kenyah languages spoken by a subgroup of the Kenyah people of Borneo.
-
C.
Kenteng Songo
Kenteng Songo is one of the main summits of Mount Merbabu, a popular hiking and volcanic mountain destination in Central Java, Indonesia.
-
D.
Kenyah Uma’ Timai
chosen
Kenyah Uma’ Timai is a specific indigenous Kenyah language variety spoken by a subgroup of the Kenyah people of Borneo.
-
E.
Bujang Ganong
Bujang Ganong is a lively, comical warrior figure in the traditional Indonesian Reog Ponorogo dance, known for his acrobatic movements, red mask, and humorous antics.
- 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_69e11e4776588190abb21e5cea79973f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15765a004819081dcdccbfd0efea7 |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:42 p.m.