Triple
T22402231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Muhu |
E553788
|
entity |
| Predicate | hasVillage |
P4011
|
FINISHED |
| Object | Koguva |
—
|
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: Koguva | Statement: [Muhu, hasVillage, Koguva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Koguva Context triple: [Muhu, hasVillage, Koguva]
-
A.
Koguva
chosen
Koguva is a historic coastal village in Estonia known for its well-preserved traditional farm architecture and role as an open-air museum on Muhu Island.
-
B.
Totaig
Totaig is a small rural settlement on the Duirinish peninsula in the Scottish Highlands, known for its scenic coastal and mountain views.
-
C.
Koja
Koja is a coastal district in North Jakarta, Indonesia, known for its dense urban neighborhoods and proximity to the city’s port and industrial areas.
-
D.
Korku
Korku is an indigenous tribal language of central India, primarily spoken by the Korku people in parts of Maharashtra and neighboring states.
-
E.
Kavim
Kavim is a crime novel by Turkish author Ahmet Ümit that blends detective fiction with social and political themes in contemporary Turkey.
- 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_69f158b4a96c8190838f5dda21c4d853 |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 16, 2026, 8:46 p.m.