Triple
T13229672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MRT Light Red Line |
E314977
|
entity |
| Predicate | fullCommercialOperationStart |
P35191
|
FINISHED |
| Object | 2021-11-29 |
—
|
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: 2021-11-29 | Statement: [MRT Light Red Line, fullCommercialOperationStart, 2021-11-29]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fullCommercialOperationStart Context triple: [MRT Light Red Line, fullCommercialOperationStart, 2021-11-29]
-
A.
commercialOperationStartUnit1
Indicates the date or time when commercial operation of Unit 1 begins.
-
B.
commercialOperationStartUnit2
Indicates the point in time when the second unit of a facility or system begins its commercial operation.
-
C.
operatorStart
Indicates the point in time or event at which an operator begins performing an action or process.
-
D.
operationStart
Indicates the point in time or event at which a specific operation or process begins.
-
E.
openedForCommercialService
chosen
Indicates that something (such as a facility, route, or service) began operating and became available for regular commercial use.
- 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_69d806affc688190a25b6ccc588e9c72 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d336ae08190bfc118cfbefddf84 |
completed | April 10, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69d98bcb21648190aef241de1e7887e2 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:21 p.m.