Triple
T28993574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhuhai railway station |
E736094
|
entity |
| Predicate | isTerminusType |
P9111
|
FINISHED |
| Object | southern terminus |
—
|
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: southern terminus | Statement: [Zhuhai railway station, isTerminusType, southern terminus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isTerminusType Context triple: [Zhuhai railway station, isTerminusType, southern terminus]
-
A.
isTerminal
Indicates that an entity represents an endpoint or final state in a process, structure, or sequence, with no further continuation beyond it.
-
B.
terminusType
chosen
Indicates the specific kind or role of an endpoint or terminal within a route, network, or process.
-
C.
isTerminalIn
Indicates that one entity functions as a terminal (end point or final element) within another entity, such as a structure, sequence, or process.
-
D.
isTerminusAccessFor
Indicates that one location or facility serves as an access point or terminal endpoint for another transportation route, service, or system.
-
E.
hasTerminusIn
Indicates that something (such as a route, line, or path) ends or has its final stopping point at a specified 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f65f7f067081909057e9c6e1fd0bdd |
completed | May 2, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:28 a.m.