Triple
T8726123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lahti |
E207135
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Lake Vesijärvi |
E509391
|
NE FINISHED |
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: Lake Vesijärvi | Statement: [Lahti, locatedOn, Lake Vesijärvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Vesijärvi Context triple: [Lahti, locatedOn, Lake Vesijärvi]
-
A.
Lake Vesijärvi
chosen
Lake Vesijärvi is a freshwater lake in southern Finland’s Lakeland region, known for its recreational use, surrounding forests, and proximity to the city of Lahti.
-
B.
Lake Vuokkijärvi
Lake Vuokkijärvi is a Finnish lake in the Kainuu region, known for its natural scenery and its proximity to the municipality of Suomussalmi.
-
C.
Lake Pihlajavesi
Lake Pihlajavesi is a large, island-rich freshwater lake in eastern Finland that forms part of the Saimaa lake system within the Finnish Lakeland region.
-
D.
Lake Jyväsjärvi
Lake Jyväsjärvi is a central Finnish lake that borders and visually defines much of the cityscape of Jyväskylä.
-
E.
Lake Ruovesi
Lake Ruovesi is a scenic lake in the Pirkanmaa region of Finland, known for its natural beauty and cultural significance as an inspiration to Finnish artists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca835811d8819081ea00fd2a2c9a1c |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d158b0481908249610458f97306 |
completed | March 31, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf6eec316c8190a681791ceefa5804 |
completed | April 3, 2026, 7:40 a.m. |
Created at: March 30, 2026, 6:36 p.m.