Triple
T14377327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Härjedalen |
E356507
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | Ljusnan |
E763086
|
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: Ljusnan | Statement: [Härjedalen, hasRiver, Ljusnan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ljusnan Context triple: [Härjedalen, hasRiver, Ljusnan]
-
A.
Ljusnan
chosen
Ljusnan is a major river in central Sweden that flows through several counties before emptying into the Gulf of Bothnia.
-
B.
Ljuset
Ljuset is a novel by Swedish author Torgny Lindgren, known for its lyrical prose and exploration of memory, faith, and rural life in northern Sweden.
-
C.
Ljusne
Ljusne is a small industrial locality in Gävleborg County, Sweden, known historically for its sawmills and pulp and paper industry along the Ljusnan River.
-
D.
Licht
Licht is Karlheinz Stockhausen’s monumental seven-opera cycle, each part associated with a day of the week and combining music, theater, and spirituality into one of the most ambitious works of 20th-century avant-garde music.
-
E.
Hohes Licht
Hohes Licht is a prominent mountain peak in the Allgäu Alps, known for its striking rocky summit and popularity among alpine hikers and climbers.
- 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.