Triple
T34745839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chuk Yuen North Estate |
E1001632
|
entity |
| Predicate | belongsToHousingSystem |
P70713
|
FINISHED |
| Object | Hong Kong public housing system |
—
|
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 public housing system | Statement: [Chuk Yuen North Estate, belongsToHousingSystem, Hong Kong public housing system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToHousingSystem Context triple: [Chuk Yuen North Estate, belongsToHousingSystem, Hong Kong public housing system]
-
A.
hasHouseSystem
Indicates that one entity possesses, uses, or is associated with a particular house system.
-
B.
memberOfEstateSystem
chosen
Indicates that an entity belongs to, is included within, or is administered as part of a particular estate system.
-
C.
hasHallOfResidence
Indicates that an institution or organization provides or is associated with a specific hall of residence for accommodation.
-
D.
hasDormitorySystem
Indicates that an institution operates or is associated with a system of dormitories for housing residents.
-
E.
hasSchoolHouseSystem
Indicates that an educational institution organizes its students into a defined house or house-like grouping system.
- 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_69f76db0367081909b57c50a7fb03025 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 3:59 p.m.