Triple
T36541008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | His Majesty the King of Saxony |
E901020
|
entity |
| Predicate | nativeTitleForm |
P186036
|
FINISHED |
| Object | König von Sachsen |
—
|
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: König von Sachsen | Statement: [His Majesty the King of Saxony, nativeTitleForm, König von Sachsen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nativeTitleForm Context triple: [His Majesty the King of Saxony, nativeTitleForm, König von Sachsen]
-
A.
nativeTitleOutcome
Indicates the result or status achieved in relation to a native or original title (such as a formal designation, rank, or work title) following some process or event.
-
B.
nativeTitleRegion
Indicates the region or area in which a title is considered native or originally used.
-
C.
nativeTitleGroup
Indicates a grouping relationship that associates entities with their titles as expressed in their original or native language.
-
D.
nativeTitleState
Indicates the state or condition of an entity’s original or native title (e.g., whether it is present, valid, active, or in a particular status).
-
E.
nativeTitleDeterminationType
Indicates the method or criteria used to determine an entity’s original or native title.
- 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_69f76e61217081908b79d610fe67b013 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c83f5960819089610ed39c839678 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:11 p.m.