Triple
T19232583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Changi Beach |
E480906
|
entity |
| Predicate | massExecutionSiteFor |
P78073
|
FINISHED |
| Object | Chinese civilians |
—
|
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: Chinese civilians | Statement: [Changi Beach, massExecutionSiteFor, Chinese civilians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: massExecutionSiteFor Context triple: [Changi Beach, massExecutionSiteFor, Chinese civilians]
-
A.
keyExecutionSite
Indicates the location or context in which a key (e.g., cryptographic or access key) is actually used or executed.
-
B.
executionBy
Indicates that one entity carries out or performs the execution (killing or implementation of a death sentence) of another entity.
-
C.
subjectOfExecution
chosen
Indicates that one entity is the object or target upon which an execution (carrying out of a death sentence) is performed by another entity.
-
D.
executionSurface
Indicates the surface or medium on which an action, process, or operation is carried out or executed.
-
E.
executionSide
Indicates which party or side in a transaction, contract, or interaction is responsible for performing or carrying out the specified action.
- 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa9fa7348190947129273d19c9a7 |
completed | April 20, 2026, 10:06 a.m. |
| PD | Predicate disambiguation | batch_69e4dcfae6f081909cc173cf71a5005c |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:25 p.m.