Triple
T25849901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 六甲山地 |
E651172
|
entity |
| Predicate | 主峰 |
P116968
|
FINISHED |
| Object | 六甲山 |
—
|
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: 六甲山 | Statement: [六甲山地, 主峰, 六甲山]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 主峰 Context triple: [六甲山地, 主峰, 六甲山]
-
A.
本山
Indicates a relationship or action involving "Benshan," but the predicate alone is too ambiguous to determine a specific relational meaning without additional context.
-
B.
mainHillName
chosen
Indicates that the subject’s primary or most prominent hill is identified by the given name.
-
C.
hasMainMountain
Indicates that an entity is primarily associated with or characterized by a specific mountain as its main or most significant mountain.
-
D.
centralPeak
Indicates that one entity is the central, elevated peak located near the middle of another entity, typically within a larger structure such as a crater or basin.
-
E.
otherMajorPeak
Indicates that one peak is another significant or prominent peak associated with, but distinct from, a given primary peak.
- 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_69e7ab39035c8190be15c8aaee1bb858 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6023ac9e48190b60639f667445ace |
completed | May 2, 2026, 1:55 p.m. |
| PD | Predicate disambiguation | batch_69f4939148dc81908706cec7d85291bc |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 7:58 a.m.