Triple
T6499143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchy of Prussia |
E148834
|
entity |
| Predicate | vassalageEnd |
P62190
|
FINISHED |
| Object | 1657 |
—
|
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: 1657 | Statement: [Duchy of Prussia, vassalageEnd, 1657]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vassalageEnd Context triple: [Duchy of Prussia, vassalageEnd, 1657]
-
A.
vassalageEndedBy
Indicates that a prior vassal relationship between two entities has been terminated by a specific third party or event.
-
B.
vassalageEndTime
chosen
Indicates the point in time at which a vassalage relationship between two entities formally ends.
-
C.
afterConquestBy
Indicates that one entity exists in a state, condition, or situation that occurs subsequent to and as a result of being conquered by another entity.
-
D.
wasKingdomUntil
Indicates that an entity functioned as a kingdom governing another entity up to a specified end time or event.
-
E.
dynastyEndedWith
Indicates that a particular dynasty concluded or came to an end with the specified ruler, event, or time period.
- 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_69c687e9ad288190bae5bcac9c8ac855 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c69f386aa08190bfc8592a92ec6339 |
completed | March 27, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69c68ab714908190aa7c2fbf64078e15 |
completed | March 27, 2026, 1:48 p.m. |
Created at: March 27, 2026, 1:41 p.m.