Triple
T12441081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bang Wa Depot |
E297270
|
entity |
| Predicate | supportsLineType |
P47205
|
FINISHED |
| Object | elevated rapid transit |
—
|
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: elevated rapid transit | Statement: [Bang Wa Depot, supportsLineType, elevated rapid transit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsLineType Context triple: [Bang Wa Depot, supportsLineType, elevated rapid transit]
-
A.
supportsLine
Indicates that one entity provides structural, functional, or conceptual backing or reinforcement to a particular line (such as a line of text, code, argument, or physical alignment).
-
B.
lineType
Indicates the specific category or style of a line used in a representation, such as its function or visual convention.
-
C.
servesLineType
chosen
Indicates that a service or entity operates or supports a specific type or category of line (e.g., transport, communication, or utility line).
-
D.
servedLineType
Indicates the type or category of service line associated with or provided in a given context.
-
E.
usesLineCharacteristic
Indicates that one entity employs or is based on a specific characteristic or property of a line.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.