Triple
T17317897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balantak people |
E420476
|
entity |
| Predicate | ethnolinguisticGroup |
P3349
|
FINISHED |
| Object | Balantak |
—
|
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: Balantak | Statement: [Balantak people, ethnolinguisticGroup, Balantak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Balantak Context triple: [Balantak people, ethnolinguisticGroup, Balantak]
-
A.
Balantak
chosen
Balantak is an Austronesian language of central Sulawesi, Indonesia, closely related to and often grouped with the Saluan language.
-
B.
Ubakala
Ubakala is a town in Abia State, southeastern Nigeria, serving as the administrative center of the Umuahia South Local Government Area.
-
C.
Balara
Balara is a municipality-level city in southeastern Nepal’s Madhesh Province, known for its agrarian economy and proximity to the Indian border.
-
D.
Kalabahi
Kalabahi is the main town and administrative center on Alor Island in Indonesia’s East Nusa Tenggara province.
-
E.
Dambal
Dambal is a historic town in Karnataka, India, renowned for its medieval temples and architectural heritage from the Western Chalukya era.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4399ea7dc8190a0ecab7534fe16c3 |
completed | April 19, 2026, 2:10 a.m. |
Created at: April 10, 2026, 5:43 a.m.