Triple
T29610121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 巴士海峽 |
E754691
|
entity |
| Predicate | 連接水域 |
P6307
|
FINISHED |
| Object | 南海 |
—
|
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: 南海 | Statement: [巴士海峽, 連接水域, 南海]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 連接水域 Context triple: [巴士海峽, 連接水域, 南海]
-
A.
connectsBodyOfWater
chosen
Indicates a relationship where one entity serves as a link or passage between two bodies of water, allowing them to be joined or interact.
-
B.
connectedBodyOfWater
Indicates that two geographic locations are linked by a continuous body of water through which water can flow between them.
-
C.
waterwayLinkBetween
Indicates a connection or linkage between two waterways, such as rivers, canals, or channels, through which water can flow or navigation can occur.
-
D.
connectsToBodyOfWaterRegion
Indicates that a region has a direct physical connection or boundary with a body of water.
-
E.
hasWatersOf
Indicates that a geographic or physical entity contains, is traversed by, or is otherwise characterized by specific bodies or types of water.
- 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_69f0ef85f62081909842b59fdf8717e1 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66dea375881909684db997861425c |
completed | May 2, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:28 p.m.