Triple
T2234653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constans |
E49250
|
entity |
| Predicate | overthrowYear |
P4401
|
FINISHED |
| Object | 350 |
—
|
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: 350 | Statement: [Constans, overthrowYear, 350]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: overthrowYear Context triple: [Constans, overthrowYear, 350]
-
A.
overthrownIn
Indicates that one entity (such as a government, leader, or regime) was removed from power or defeated in a specific event, context, or time period represented by the other entity.
-
B.
overthrewGovernment
Indicates that an entity forcibly removed an existing government from power, typically replacing it with a new regime.
-
C.
revolutionVictoryYear
chosen
Indicates the year in which a revolution achieved victory or successfully overthrew the existing regime.
-
D.
dictatorshipEndYear
Indicates the calendar year in which a particular dictatorship or dictatorial regime came to an end.
-
E.
overthrownWithHelpOf
Indicates that one entity was removed from power or defeated through the assistance, support, or intervention of another specified entity.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc09297a481909e8fe6ec645de616 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.