Triple
T18024934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Akagi multi-summit range |
E431220
|
entity |
| Predicate | hasSummits |
P77438
|
FINISHED |
| Object | multiple mountain summits |
—
|
LITERAL 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: multiple mountain summits | Statement: [Mount Akagi multi-summit range, hasSummits, multiple mountain summits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSummits Context triple: [Mount Akagi multi-summit range, hasSummits, multiple mountain summits]
-
A.
hasMultipleSummits
chosen
Indicates that an entity (such as a mountain or peak) consists of more than one distinct summit or high point.
-
B.
hasSummitFacility
Indicates that one entity possesses or provides a facility or infrastructure located at the summit of another entity (such as a mountain, hill, or peak).
-
C.
hasHigherSummit
Indicates that one entity’s summit is higher in elevation than another entity’s summit.
-
D.
hasTwoSummits
Indicates that an entity (typically a mountain or peak) possesses exactly two distinct summits.
-
E.
hasSummitViewsOf
Indicates that from the summit of one location, there are views overlooking or directed toward another location.
- 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_69d8b9050fb48190890155145deb0a66 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c554348190bd0df06d0cfe188e |
completed | April 19, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_69e3f904b8048190add43883cd7cb191 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:24 a.m.