Triple
T8882790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ehrwald |
E211450
|
entity |
| Predicate | hasNearbyMountain |
P651
|
FINISHED |
| Object | Zugspitze |
E41130
|
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: Zugspitze | Statement: [Ehrwald, hasNearbyMountain, Zugspitze]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zugspitze Context triple: [Ehrwald, hasNearbyMountain, Zugspitze]
-
A.
Zugspitze
chosen
Zugspitze is the highest mountain in Germany, located in the Bavarian Alps near the Austrian border.
-
B.
Königspitze
Königspitze is a prominent high peak in the Eastern Alps of northern Italy, renowned among mountaineers for its steep faces and challenging climbing routes.
-
C.
Schneefernerkopf
Schneefernerkopf is a prominent peak in the Bavarian Alps near Germany’s highest mountain, Zugspitze, known for its rugged terrain and alpine scenery.
-
D.
Lenzspitze
Lenzspitze is a prominent high-altitude peak in the Swiss Pennine Alps, known for its sharp ridges and challenging alpine climbing routes.
-
E.
Watzmann
Watzmann is a prominent mountain massif in the Bavarian Alps, renowned for its striking peaks and dramatic presence above the town of Berchtesgaden.
- 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc616a01f48190b8bbde0e898a38c7 |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d02f88db0881909975af03ed2f3d84 |
completed | April 3, 2026, 9:22 p.m. |
Created at: March 30, 2026, 6:53 p.m.