Triple
T35170366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsz Ching Estate |
E1015528
|
entity |
| Predicate | hasEstateCategory |
P33508
|
FINISHED |
| Object | Public Rental Housing Estate in Wong Tai Sin District |
—
|
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: Public Rental Housing Estate in Wong Tai Sin District | Statement: [Tsz Ching Estate, hasEstateCategory, Public Rental Housing Estate in Wong Tai Sin District]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEstateCategory Context triple: [Tsz Ching Estate, hasEstateCategory, Public Rental Housing Estate in Wong Tai Sin District]
-
A.
hasEstateType
chosen
Indicates that an entity possesses or is associated with a particular category or type of estate.
-
B.
hasEstateComponent
Indicates that one entity includes or is composed of another entity as a component or part of an estate.
-
C.
hasAssociatedEstate
Indicates that one entity is linked to, or has responsibility for, a particular estate or property.
-
D.
hasEstateManager
Indicates that an entity is responsible for managing, overseeing, or administering the estate or property of another entity.
-
E.
hadEstate
Indicates that an entity possessed or owned a particular estate or landed property.
- 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_69f76ddbfde081908bffc91572368289 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f78f63c8788190b253a18de5ca1312 |
completed | May 3, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69f78e2d71248190b850c2802ec170c0 |
completed | May 3, 2026, 6:04 p.m. |
Created at: May 3, 2026, 4:02 p.m.