Triple
T790761
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tyrolean Alps |
E16907
|
entity |
| Predicate | containsPeak |
P8205
|
FINISHED |
| Object | Großglockner |
E17969
|
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: Großglockner | Statement: [Tyrolean Alps, containsPeak, Großglockner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Großglockner Context triple: [Tyrolean Alps, containsPeak, Großglockner]
-
A.
Grossglockner
chosen
Grossglockner is the tallest mountain in Austria and a prominent peak of the Hohe Tauern range in the Central Eastern Alps.
-
B.
Wildspitze
Wildspitze is a prominent mountain in the Ötztal Alps of Tyrol, Austria, known as one of the country's highest and most popular alpine climbing peaks.
-
C.
Zugspitze
Zugspitze is the highest mountain in Germany, located in the Bavarian Alps near the Austrian border.
-
D.
Vršič Pass
Vršič Pass is a high mountain pass in northwestern Slovenia that serves as a key road connection through the Julian Alps between the Sava and Soča river valleys.
-
E.
Konradshöhe
Konradshöhe is a leafy, riverside locality in the northwest of Berlin known for its tranquil, village-like character within the borough of Reinickendorf.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a79754988190ab494b1c54d6a2a4 |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7cf4f602481908f9c399063a605b9 |
completed | March 4, 2026, 6:21 a.m. |
Created at: March 1, 2026, 7:38 p.m.