Triple
T20137656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harju maakond |
E491063
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Naissaar |
—
|
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: Naissaar | Statement: [Harju maakond, contains, Naissaar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naissaar Context triple: [Harju maakond, contains, Naissaar]
-
A.
Naissaar
chosen
Naissaar is a forested Estonian island in the Baltic Sea known for its military history, nature reserves, and proximity to Tallinn.
-
B.
Saaremaa
Saaremaa is the largest island of Estonia, known for its rugged coastline, medieval Kuressaare Castle, and distinctive windmills and juniper landscapes.
-
C.
Ruhnu
Ruhnu is a small Estonian island in the Gulf of Riga, known for its remote location, traditional wooden lighthouse and church, and unique cultural heritage.
-
D.
Kuressaare
Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
-
E.
Vilsandi Island
Vilsandi Island is a small Baltic Sea island off the western coast of Estonia, known for its rich birdlife, coastal landscapes, and role as a core area of Vilsandi National Park.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6676879f48190a59da04393d2a8cc |
completed | April 20, 2026, 5:50 p.m. |
Created at: April 11, 2026, 11:32 p.m.