Triple
T27353156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Harbour Crossing Hong Kong portal |
E685615
|
entity |
| Predicate | isExitOf |
P29827
|
FINISHED |
| Object | Eastern Harbour Crossing |
—
|
NE NERFINISHED |
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: Eastern Harbour Crossing | Statement: [Eastern Harbour Crossing Hong Kong portal, isExitOf, Eastern Harbour Crossing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isExitOf Context triple: [Eastern Harbour Crossing Hong Kong portal, isExitOf, Eastern Harbour Crossing]
-
A.
hasExitFor
chosen
Indicates that something provides or includes a specific exit intended for a particular destination, purpose, or user.
-
B.
isMajorExitOf
Indicates that one location serves as a primary or significant exit point from another location or route.
-
C.
exitTo
Indicates that one location or entity serves as a passage or route leading directly to another location or entity.
-
D.
hasEastExit
Indicates that an entity has an exit or passage leading to the east.
-
E.
hasNumberedExit
Indicates that an entity (such as a road or highway) includes or is associated with an exit that has an assigned number.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62c1b91e881908798e4f00723efcb |
completed | May 2, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:49 a.m.