Triple
T4240420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Mälaren |
E95397
|
entity |
| Predicate | hasCityOnShore |
P969
|
FINISHED |
| Object | Sigtuna |
E25045
|
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: Sigtuna | Statement: [Lake Mälaren, hasCityOnShore, Sigtuna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sigtuna Context triple: [Lake Mälaren, hasCityOnShore, Sigtuna]
-
A.
Borgholm
Borgholm is a small coastal town in southeastern Sweden, known as a popular summer resort and for the nearby Borgholm Castle ruins on the island of Öland.
-
B.
Kalmar
Kalmar is a historic coastal city in southeastern Sweden known for its medieval castle, role in the Kalmar Union, and connection to the island of Öland.
-
C.
Sigtuna Municipality
chosen
Sigtuna Municipality is a local government area in east-central Sweden known for encompassing the historic town of Sigtuna, one of the country’s oldest urban settlements.
-
D.
Hudiksvall
Hudiksvall is a coastal town in east-central Sweden known for its historic wooden buildings and harbor on the Gulf of Bothnia.
-
E.
Strömstad
Strömstad is a coastal town and municipality in western Sweden, near the Norwegian border, known for its archipelago, tourism, and ferry connections.
- 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_69b3453d91548190b4d4ef8fe52aa2ac |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e77fb5c8190b298818acb68ff63 |
completed | March 12, 2026, 11:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a86fe7708190a64ba187fb302c9a |
completed | March 14, 2026, 6:26 p.m. |
Created at: March 12, 2026, 11:05 p.m.