Triple
T20797628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karo Regency |
E511952
|
entity |
| Predicate | regencySeat |
P71777
|
FINISHED |
| Object | Kabanjahe |
—
|
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: Kabanjahe | Statement: [Karo Regency, regencySeat, Kabanjahe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kabanjahe Context triple: [Karo Regency, regencySeat, Kabanjahe]
-
A.
Kabanjahe
chosen
Kabanjahe is a principal town and administrative center in North Sumatra, Indonesia, known as a hub of Karo culture and gateway to the surrounding highland region.
-
B.
Kaltungo
Kaltungo is a town and administrative center in northeastern Nigeria known for its role as one of the local government areas within Gombe State.
-
C.
Barawa
Barawa is a historic coastal city in southern Somalia known as an important port and cultural center of the Bravanese people.
-
D.
Barawa
Barawa is a West Chadic language spoken in parts of Nigeria, belonging to the Afroasiatic language family.
-
E.
Kumba
Kumba is a major town in southwestern Cameroon known as a commercial hub and cultural crossroads where languages like Cameroonian Pidgin English are widely used.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2ae2c4c819087f620df31dc1aba |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:39 p.m.