Triple
T36209102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shek Kong Barracks |
E1047487
|
entity |
| Predicate | transferDateToPLA |
P200193
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Shek Kong Barracks, transferDateToPLA, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transferDateToPLA Context triple: [Shek Kong Barracks, transferDateToPLA, 1997]
-
A.
dateOfTransfer
Indicates the specific date on which a transfer of something (such as ownership, rights, or funds) from one party to another takes place.
-
B.
transferToUnitedStatesDate
Indicates the date on which something is transferred or moved to the United States.
-
C.
transferAfter
Indicates that one entity transfers something to another entity only after a specified event or condition has occurred.
-
D.
officeTransferredAt
Indicates the time or date at which an office (or official position) was transferred from one holder or location to another.
-
E.
UNSeatTransferDate
Indicates the date on which a seat is transferred from one holder to another.
- F. None of above. chosen
Provenance (4 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_69f76e4214748190a76c986d2a1838c2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff79e7206c8190a809b5f2a6261378 |
completed | May 9, 2026, 6:16 p.m. |
| PD | Predicate disambiguation | batch_69ff798356b881908645074fb3a96517 |
completed | May 9, 2026, 6:14 p.m. |
| PDg | Predicate description generation | batch_69ff79e645c08190a974b5239efac35b |
completed | May 9, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:09 p.m.