Triple
T34745964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kowloon Walled City |
E1001634
|
entity |
| Predicate | evictionCompensationPaidBy |
P12961
|
FINISHED |
| Object | British Hong Kong Government |
—
|
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: British Hong Kong Government | Statement: [Kowloon Walled City, evictionCompensationPaidBy, British Hong Kong Government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evictionCompensationPaidBy Context triple: [Kowloon Walled City, evictionCompensationPaidBy, British Hong Kong Government]
-
A.
evictionType
Indicates the specific kind or category of eviction that applies in a given eviction event or relationship.
-
B.
evictionOccurredIn
Indicates that an eviction event took place within or at a specified location or jurisdiction.
-
C.
previouslyPaidTo
Indicates that a payment was made in the past from one entity to another.
-
D.
paidBy
chosen
Indicates that a payment or financial obligation is made or settled by the specified entity.
-
E.
compensatoryType
Indicates the specific category or nature of compensation associated with an action, obligation, or remedy in the relationship.
- 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_69f77ffa6b68819090257fed3802c239 |
completed | May 3, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69f7795978c481909e152cd1bd02dd07 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.