Triple
T1965024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Confession of Mikhail Bakunin |
E42668
|
entity |
| Predicate | writtenAfter |
P23830
|
FINISHED |
| Object | arrest of Mikhail Bakunin |
—
|
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: arrest of Mikhail Bakunin | Statement: [Confession of Mikhail Bakunin, writtenAfter, arrest of Mikhail Bakunin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: writtenAfter Context triple: [Confession of Mikhail Bakunin, writtenAfter, arrest of Mikhail Bakunin]
-
A.
writtenDuring
Indicates that the creation or authorship of something took place within a specified time period or historical event.
-
B.
laterWrittenIn
chosen
Indicates that one text or version was written at a later time than another, establishing a chronological order between the writings.
-
C.
writtenAtEvent
Indicates that a writing or inscription activity occurred during or in connection with a specific event.
-
D.
hasDateWritten
Indicates that something is associated with the specific date on which it was written.
-
E.
hasWrittenFor
Indicates that one entity has created written content (such as articles, stories, or texts) for or on behalf of another entity, typically a publication, organization, or platform.
- 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_69a88711151c8190940b2572095059d7 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb3aeb20081908b0d447d9fcdbaad |
completed | March 7, 2026, 5:12 a.m. |
| PD | Predicate disambiguation | batch_69abaff7d4a48190ab0d51aefb1c4e31 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:36 p.m.