Triple
T20792128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toba Batak |
E511803
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Samosir dialect |
—
|
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: Samosir dialect | Statement: [Toba Batak, hasDialect, Samosir dialect]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samosir dialect Context triple: [Toba Batak, hasDialect, Samosir dialect]
-
A.
Batak languages
The Batak languages are a group of closely related Austronesian languages spoken primarily by the Batak people of North Sumatra, Indonesia.
-
B.
Wangi-Wangi dialect
The Wangi-Wangi dialect is a regional variety of the Tukang Besi language spoken by communities on Wangi-Wangi Island in Southeast Sulawesi, Indonesia.
-
C.
Toba Batak language
chosen
Toba Batak language is an Austronesian language spoken primarily by the Toba Batak people of North Sumatra, Indonesia, known for its rich oral tradition and distinctive Batak script.
-
D.
Nias language
Nias language is an Austronesian language spoken primarily on Nias Island off the western coast of Sumatra in Indonesia, known for its complex phonology and distinctive grammatical features.
-
E.
Simalungun language
The Simalungun language is an Austronesian language spoken by the Simalungun subgroup of the Batak people in North Sumatra, Indonesia.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2910d488190bc4be37512effc86 |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.