Triple
T14377372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Siljan |
E356508
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Rättvik |
E356510
|
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: Rättvik | Statement: [Lake Siljan, locatedNear, Rättvik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rättvik Context triple: [Lake Siljan, locatedNear, Rättvik]
-
A.
Rättvik
chosen
Rättvik is a small town in central Sweden known for its traditional Swedish culture, lakeside setting on Lake Siljan, and historic wooden pier.
-
B.
Tjaden
Tjaden is a former locksmith and fellow German soldier in Erich Maria Remarque’s novel "All Quiet on the Western Front," known for his voracious appetite, sharp tongue, and deep camaraderie with Paul Bäumer.
-
C.
Tjaden
Tjaden is the surname of American actress and singer Janis Paige, known for her work in film, television, and Broadway.
-
D.
The Righteous
The Righteous is a film written by and starring Mark O'Brien, known as a brooding psychological horror drama with strong religious and moral themes.
-
E.
Alværn
Alværn is a small settlement in Nesodden municipality in Viken county, Norway, known primarily as a residential area within commuting distance of Oslo.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c5728fc819089ef3c7c34b10101 |
completed | May 8, 2026, 2:37 a.m. |
Created at: April 10, 2026, 1:16 a.m.