Triple
T20282437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jungfraufirn |
E503182
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | Ewigschneefäld |
—
|
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: Ewigschneefäld | Statement: [Jungfraufirn, connectedTo, Ewigschneefäld]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ewigschneefäld Context triple: [Jungfraufirn, connectedTo, Ewigschneefäld]
-
A.
Ewigschneefäld
chosen
Ewigschneefäld is a high-altitude glacier in the Bernese Alps of Switzerland, known for its extensive ice fields and proximity to major peaks like the Fiescherhorn.
-
B.
Frostlendet
Frostlendet is a glaciated valley or ice-filled area located within Antarctica’s Mühlig-Hofmann Mountains in Queen Maud Land.
-
C.
Frost Valley
Frost Valley is a scenic valley area in the Catskill Mountains of New York, known for its forests, streams, and outdoor recreation opportunities.
-
D.
Talgje
Talgje is an island in Rogaland county, Norway, known for its historic church, fertile farmland, and scenic coastal landscape.
-
E.
Schneekoppe
Schneekoppe is the highest peak in the Krkonoše (Giant) Mountains and the Czech Republic, located on the border between the Czech Republic and Poland.
- 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_69e0b4b0e79c8190bd61f22ef1329fa8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6768f86448190842389a98b93a918 |
completed | April 20, 2026, 6:55 p.m. |
Created at: April 16, 2026, 10:40 a.m.