Triple
T22400860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Tapanuli Regency |
E553753
|
entity |
| Predicate | historicalRegion |
P915
|
FINISHED |
| Object | Tapanuli |
—
|
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: Tapanuli | Statement: [South Tapanuli Regency, historicalRegion, Tapanuli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tapanuli Context triple: [South Tapanuli Regency, historicalRegion, Tapanuli]
-
A.
Tapanuli
chosen
Tapanuli is a region in northern Sumatra, Indonesia, known for its Batak cultural heritage and distinct highland landscapes.
-
B.
North Tapanuli
North Tapanuli is a regency in North Sumatra, Indonesia, known for its highland landscapes, Batak Toba culture, and proximity to Lake Toba.
-
C.
Toba Batak
Toba Batak is an Austronesian language spoken primarily by the Toba Batak people of North Sumatra, Indonesia.
-
D.
Kerinci
Kerinci is an Austronesian language spoken primarily in the Kerinci region of central Sumatra, Indonesia, known for its distinctive phonology and dialect diversity.
-
E.
Pakpak-Dairi
Pakpak-Dairi is an Austronesian language spoken by the Pakpak (Dairi) people of northern 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b39c908190a735aa860d733869 |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 16, 2026, 8:46 p.m.