Triple
T34275071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ludwig II. von Ungarn und Böhmen |
E879428
|
entity |
| Predicate | Herrschaftsgebiet |
P68921
|
FINISHED |
| Object | Königreich Ungarn |
—
|
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: Königreich Ungarn | Statement: [Ludwig II. von Ungarn und Böhmen, Herrschaftsgebiet, Königreich Ungarn]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Herrschaftsgebiet Context triple: [Ludwig II. von Ungarn und Böhmen, Herrschaftsgebiet, Königreich Ungarn]
-
A.
realmRuled
chosen
Indicates that one entity serves as the sovereign or governing ruler over a particular realm, territory, or domain.
-
B.
kingdom
Indicates that an entity is classified within a particular biological kingdom in a taxonomic hierarchy.
-
C.
governingEmpire
Indicates that one entity serves as the ruling imperial power that controls or governs another entity.
-
D.
realmConqueredBy
Indicates that a particular realm or territory has been taken over and brought under the control of a specified conqueror.
-
E.
regionOfDynasty
Indicates the geographic region or area in which a given dynasty held power or was primarily based.
- 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_69f349b5f6648190b9420d94a4cd16e0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71362f1448190985a80ce7af475cb |
completed | May 3, 2026, 9:20 a.m. |
| PD | Predicate disambiguation | batch_69f7127884388190884f23d181a65d19 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:56 a.m.