Triple
T23485669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nguyễn Cao Kỳ |
E570526
|
entity |
| Predicate | officeEndTime (Prime Minister of South Vietnam) |
P101927
|
FINISHED |
| Object | 1967-10-31 |
—
|
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: 1967-10-31 | Statement: [Nguyễn Cao Kỳ, officeEndTime (Prime Minister of South Vietnam), 1967-10-31]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEndTime (Prime Minister of South Vietnam) Context triple: [Nguyễn Cao Kỳ, officeEndTime (Prime Minister of South Vietnam), 1967-10-31]
-
A.
officeEndTime (Vice President of South Vietnam)
Indicates the time at which the Vice President of South Vietnam’s term in office concluded.
-
B.
officeStartTime (Vice President of South Vietnam)
Indicates the date and time at which an individual began serving as Vice President of South Vietnam.
-
C.
officeEndTime (President of the Republic of China)
Indicates the time at which a President of the Republic of China’s term in office concludes.
-
D.
officeEndTime (Prime Minister, first term)
Indicates the time at which the Prime Minister’s first term in office officially ended.
-
E.
officeEndTime (Prime Minister)
chosen
Indicates the time at which the Prime Minister’s term in office concludes.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7538a8c8190b7effcc39a3f9787 |
completed | April 29, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69f0620ac3608190b36916261ea50f54 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:03 p.m.