Triple
T11737361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henry II, Holy Roman Emperor |
E279063
|
entity |
| Predicate | succeededAsDukeOfBavaria |
P101077
|
FINISHED |
| Object | 995 |
—
|
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: 995 | Statement: [Henry II, Holy Roman Emperor, succeededAsDukeOfBavaria, 995]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: succeededAsDukeOfBavaria Context triple: [Henry II, Holy Roman Emperor, succeededAsDukeOfBavaria, 995]
-
A.
reignAsDukeOfBavariaTo
Indicates that one entity holds and exercises the title and authority of Duke of Bavaria over another entity (typically a territory or domain).
-
B.
reignAsDukeOfBavariaFrom
Indicates that a person held and exercised the title and authority of Duke of Bavaria starting from a specified time.
-
C.
succeededAsDukeOfSwabiaBy
Indicates that one entity became the next Duke of Swabia following another entity in that title or position.
-
D.
succeededAsDuke
Indicates that one individual assumed the title and position of duke previously held by another, directly following them in that role.
-
E.
succeededByAsKingOfGermany
Indicates that one person directly followed another as the reigning King of Germany.
- 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_69d6aaffec6881908bead509e8621742 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4ef1c4881909ad36dc27b1fe193 |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a7f51248190bf492bd7509b5413 |
completed | April 10, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69d890458d948190b15054c9ba0fd923 |
completed | April 10, 2026, 5:53 a.m. |
Created at: April 8, 2026, 9:41 p.m.