Triple
T19581756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kumna manor |
E490006
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Kumna |
—
|
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: Kumna | Statement: [Kumna manor, locatedIn, Kumna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kumna Context triple: [Kumna manor, locatedIn, Kumna]
-
A.
Kumna
chosen
Kumna is a village located in Harku Parish in northern Estonia.
-
B.
Dumna
Dumna is a locality in India known for its proximity to Dumna Airport and its role as a regional transport and residential area.
-
C.
Dumna
Dumna is a dialect of the Southern Valley Yokuts language traditionally spoken by an Indigenous community in California’s San Joaquin Valley.
-
D.
Kolokuma
Kolokuma is a dialect of the Ijo language spoken primarily by the Kolokuma people in Nigeria’s Bayelsa State.
-
E.
Kundla
Kundla is a surname most notably associated with John Kundla, the Hall of Fame head coach who led the Minneapolis Lakers to multiple early NBA championships.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6404e18f88190b7fec59499dd25e8 |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:42 p.m.