Triple
T12229135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong Link Road |
E291428
|
entity |
| Predicate | isPartOfBorderCrossingCorridor |
P103910
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Hong Kong Link Road, isPartOfBorderCrossingCorridor, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfBorderCrossingCorridor Context triple: [Hong Kong Link Road, isPartOfBorderCrossingCorridor, yes]
-
A.
hasBorderCrossing
Indicates that there exists a point or facility where movement or transit is possible between the boundaries of two adjacent regions or jurisdictions.
-
B.
hasRailBorderCrossing
Indicates that two places are connected by at least one official border crossing that is served by rail transport.
-
C.
nearBorderCrossing
Indicates that an entity is located close to a border crossing point between two regions or countries.
-
D.
hasBorderCrossingFunction
Indicates that an entity serves as a location or facility where people, goods, or vehicles can legally cross a border between jurisdictions.
-
E.
crossBorderFacilityLocatedIn
Indicates that a cross-border facility is geographically situated within a specified territorial or administrative area.
- F. None of above. chosen
Provenance (4 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d924a3973c8190a882046963b320fb |
completed | April 10, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69d91c41bcbc81909782f4e3c571b218 |
completed | April 10, 2026, 3:50 p.m. |
| PDg | Predicate description generation | batch_69d92468052c819090546f36d009a64f |
completed | April 10, 2026, 4:25 p.m. |
Created at: April 8, 2026, 9:51 p.m.