Triple
T15612222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kreuzeck |
E375324
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Alpspitze |
E378310
|
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: Alpspitze | Statement: [Kreuzeck, near, Alpspitze]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alpspitze Context triple: [Kreuzeck, near, Alpspitze]
-
A.
Alpspitze
chosen
Alpspitze is a prominent pyramid-shaped peak in the Bavarian Alps of Germany, popular for hiking, climbing, and skiing.
-
B.
Hochalmspitze
Hochalmspitze is a prominent mountain in the Austrian Alps, renowned for its glaciated summit and challenging alpine climbing routes.
-
C.
Parseierspitze
Parseierspitze is a prominent mountain peak in the Austrian Alps, noted for its challenging climbs and striking alpine scenery.
-
D.
Birkkarspitze
Birkkarspitze is a prominent Alpine peak in the Karwendel range on the border of Austria and Germany, popular with experienced hikers and mountaineers.
-
E.
Alpstein
Alpstein is a picturesque subrange of the Alps in northeastern Switzerland, known for its dramatic limestone peaks, hiking trails, and traditional Appenzell landscapes.
- 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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e8148a0819087d6d69cc84487ca |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ecba8d08190998fc0688663a328 |
completed | May 9, 2026, 5:28 p.m. |
Created at: April 10, 2026, 4:13 a.m.