Triple
T12713641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Ferry |
E303782
|
entity |
| Predicate | hasSignificantViewOf |
P854
|
FINISHED |
| Object | Hong Kong skyline |
—
|
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: Hong Kong skyline | Statement: [Star Ferry, hasSignificantViewOf, Hong Kong skyline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSignificantViewOf Context triple: [Star Ferry, hasSignificantViewOf, Hong Kong skyline]
-
A.
hasViewThrough
Indicates that one entity can be seen or visually perceived through another entity acting as an intermediate medium or opening.
-
B.
hasView
chosen
Indicates that one entity provides a visual perspective or outlook onto another entity or scene.
-
C.
hasSignificant
Indicates that one entity possesses or exhibits a level of importance, impact, or relevance that is notably large or meaningful in relation to another entity or context.
-
D.
hasSee
Indicates that one entity has perceived or visually observed another entity.
-
E.
hasViewingSide
Indicates that one entity serves as the side or surface of another entity that is intended to be viewed or observed.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9620a7554819083784897ff690652 |
completed | April 10, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:23 p.m.