Triple
T2234901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kwang-Chou-Wan |
E49256
|
entity |
| Predicate | leaseEnd |
P11097
|
FINISHED |
| Object | 1945 |
—
|
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: 1945 | Statement: [Kwang-Chou-Wan, leaseEnd, 1945]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leaseEnd Context triple: [Kwang-Chou-Wan, leaseEnd, 1945]
-
A.
leaseAgreement
Indicates a contractual relationship in which one party grants another the right to use an asset or property for a specified period in exchange for agreed payments or conditions.
-
B.
wasLeasedFor
Indicates that one entity was leased in exchange for a specified payment amount, purpose, or consideration.
-
C.
leaseOrigin
Indicates that one entity is the original source or starting point from which a lease agreement or leasing arrangement is derived.
-
D.
tenantsEnd
Indicates that a tenancy or lease relationship between parties comes to an end at a specified time or under certain conditions.
-
E.
deFactoEndDate
chosen
Indicates the date on which a relationship, status, or condition effectively ended in practice, regardless of any formal or official end date.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc09297a481909e8fe6ec645de616 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.