Triple
T26890816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nguyễn Bá Cẩn |
E677164
|
entity |
| Predicate | endCauseOfOffice |
P34754
|
FINISHED |
| Object | Fall of Saigon |
—
|
NE NERFINISHED |
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: Fall of Saigon | Statement: [Nguyễn Bá Cẩn, endCauseOfOffice, Fall of Saigon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endCauseOfOffice Context triple: [Nguyễn Bá Cẩn, endCauseOfOffice, Fall of Saigon]
-
A.
causeOfRemovalFromOffice
Indicates the reason or factor that led to an individual being removed from an official position or office.
-
B.
causeOfEndOfPresidency
chosen
Indicates the event, action, or circumstance that directly led to the termination of a person’s presidency.
-
C.
reasonForAssumingOffice
Indicates the circumstance, cause, or justification that led an entity to take up or begin holding a particular office or position.
-
D.
termLimitReasonForLeavingOffice
Indicates that an officeholder left their position specifically because they reached a legally or formally imposed term limit.
-
E.
end cause
Indicates that one event or action brings about the termination or cessation of another event, state, or process.
- 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_69eee9bc0c90819085608c8bdc513a57 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61f67b7bc8190b6783805560aee6a |
completed | May 2, 2026, 3:59 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:44 a.m.