Triple
T20357403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lääne-Viru County |
E496685
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Kunda |
—
|
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: Kunda | Statement: [Lääne-Viru County, contains, Kunda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kunda Context triple: [Lääne-Viru County, contains, Kunda]
-
A.
Kunda
chosen
Kunda is a small industrial town in northern Estonia known for its cement industry and archaeological significance.
-
B.
Kunda
Kunda is the sacred stepped water tank associated with the Modhera Sun Temple in Gujarat, India, used historically for ritual bathing and religious ceremonies.
-
C.
Kundina
Kundina was an ancient Indian city historically associated with the Yadava dynasty and early trade and political networks in central India.
-
D.
Kaonde
Kaonde is a Bantu language spoken primarily by the Kaonde people of northwestern Zambia and parts of the Democratic Republic of the Congo.
-
E.
Lunda
Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67854c0448190ab10363f8a218afb |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.