Triple
T31077039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theuderic II |
E791993
|
entity |
| Predicate | orderedDeathOf |
P129786
|
FINISHED |
| Object | Desiderius of Vienne |
—
|
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: Desiderius of Vienne | Statement: [Theuderic II, orderedDeathOf, Desiderius of Vienne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orderedDeathOf Context triple: [Theuderic II, orderedDeathOf, Desiderius of Vienne]
-
A.
ordersDeathOf
chosen
Indicates that one entity commands or authorizes the killing or execution of another entity.
-
B.
afterDeathOf
Indicates that one event, state, or condition occurs subsequent to and as a result of the death of a specified entity.
-
C.
completionAfterDeathOf
Indicates that one event, process, or work is completed only after the death of a specified person.
-
D.
containsDeathOf
Indicates that the subject includes, depicts, or involves the death of the referenced entity.
-
E.
onceDeceased
Indicates that an entity was previously dead at some point in time, regardless of its current state.
- 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc53f4f881908dcc698687bbb64d |
completed | May 3, 2026, 7:42 a.m. |
Created at: April 29, 2026, 9:02 p.m.