Triple
T23406696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kenting National Park |
E559953
|
entity |
| Predicate | southernmostNationalParkOf |
P70550
|
FINISHED |
| Object | Taiwan |
—
|
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: Taiwan | Statement: [Kenting National Park, southernmostNationalParkOf, Taiwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: southernmostNationalParkOf Context triple: [Kenting National Park, southernmostNationalParkOf, Taiwan]
-
A.
southernmostInhabitedIslandOf
Indicates that one island is the southernmost inhabited island within the territory, region, or jurisdiction of another entity.
-
B.
southernmostDistrictOf
Indicates that one district is the geographically furthest south within the boundaries of a specified larger region or entity.
-
C.
southernmostCountry
Indicates that one country is located farther south than any other country within a specified set or region.
-
D.
southernmostMunicipalityOf
Indicates that one municipality is the geographically furthest south within the boundaries of another administrative or territorial entity.
-
E.
southernmost
chosen
Indicates that one entity is located farther to the south than all other comparable entities in a given set or context.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50e607c8190ba0a22e89862a2d9 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:38 p.m.