Triple
T29578024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kampenwand |
E753496
|
entity |
| Predicate | summitCrossVisibleFrom |
P103083
|
FINISHED |
| Object | Chiemgau plain |
—
|
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: Chiemgau plain | Statement: [Kampenwand, summitCrossVisibleFrom, Chiemgau plain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: summitCrossVisibleFrom Context triple: [Kampenwand, summitCrossVisibleFrom, Chiemgau plain]
-
A.
summitAccessibleFrom
Indicates that a summit can be reached or accessed starting from a specified location or route.
-
B.
hasSummitViewsOf
Indicates that from the summit of one location, there are views overlooking or directed toward another location.
-
C.
hasSummitViewsVia
chosen
Indicates a relationship where one location offers views of a summit when accessed or observed via a particular route, vantage point, or intermediary location.
-
D.
hasSummitCross
Indicates that a mountain or peak is topped by a summit cross installed at or near its highest point.
-
E.
summitExposure
Indicates the degree and nature of environmental exposure (e.g., wind, weather, openness) experienced at or near a summit.
- F. None of above.
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_69f0ef80bf8c8190ad286e99f7df0c63 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:04 p.m.