Triple
T14565507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 東沙環礁 |
E341773
|
entity |
| Predicate | 地質成因 |
P33784
|
FINISHED |
| Object | 珊瑚礁堆積而成 |
—
|
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: 珊瑚礁堆積而成 | Statement: [東沙環礁, 地質成因, 珊瑚礁堆積而成]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 地質成因 Context triple: [東沙環礁, 地質成因, 珊瑚礁堆積而成]
-
A.
causesGeologicalProcess
Indicates that one entity brings about, initiates, or is responsible for a geological process occurring in another or in the environment.
-
B.
hasGeologicalNature
Indicates that something possesses a specific geological character, composition, or formation type.
-
C.
geologicalFormationProcess
chosen
Indicates the natural geological process or set of processes by which a particular geological formation came into existence.
-
D.
geologicalSystem
Indicates that one entity is a geological system (e.g., rock units, structures, or processes forming a coherent geologic framework) associated with or characterizing the other entity.
-
E.
geologicalRole
Indicates the functional or classificatory role an entity plays within geological processes, structures, or contexts.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb38c6350819091090ffd15772f6f |
completed | April 14, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69de5c57489c8190b57917be1dba6ae6 |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:23 a.m.