Triple
T35881080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konrad III the Old |
E1037507
|
entity |
| Predicate | predecessorAsDukeOfOleśnica |
P195659
|
FINISHED |
| Object | Konrad V Kantner |
—
|
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: Konrad V Kantner | Statement: [Konrad III the Old, predecessorAsDukeOfOleśnica, Konrad V Kantner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorAsDukeOfOleśnica Context triple: [Konrad III the Old, predecessorAsDukeOfOleśnica, Konrad V Kantner]
-
A.
predecessorAsDukeOfSilesia
Indicates that one entity previously held the title of Duke of Silesia immediately before another entity.
-
B.
predecessorAsKingOfPoland
Indicates that one person previously held the position of King of Poland immediately before another person.
-
C.
successorAsDukeOfLegnica
Indicates that one entity became the next Duke of Legnica following another entity in the line of succession.
-
D.
predecessorAsDukeOfPrussia
Indicates that one entity previously held the title of Duke of Prussia immediately before another entity.
-
E.
predecessorAsDukeOfSaxony
Indicates that one entity previously held the title of Duke of Saxony immediately before another entity.
- F. None of above. chosen
Provenance (4 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_69f76e1f4d748190bb55594d8441d70e |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fddd373cdc8190be1b12e70e4deb1f |
completed | May 8, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_69fddc6915a88190ad41e379aa3ede13 |
completed | May 8, 2026, 12:51 p.m. |
| PDg | Predicate description generation | batch_69fddd364c1481908794c9d423bdc2d7 |
completed | May 8, 2026, 12:55 p.m. |
Created at: May 3, 2026, 4:06 p.m.