Triple
T6618814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Saxony |
E149622
|
entity |
| Predicate | nobleHouseContext |
P13617
|
FINISHED |
| Object | various Saxon ruling dynasties |
—
|
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: various Saxon ruling dynasties | Statement: [Duchess of Saxony, nobleHouseContext, various Saxon ruling dynasties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nobleHouseContext Context triple: [Duchess of Saxony, nobleHouseContext, various Saxon ruling dynasties]
-
A.
nobleHouseType
Indicates the specific category or classification of a noble house (e.g., royal, ducal, baronial) within a hierarchy or system of nobility.
-
B.
notableNoble
Indicates that an entity is a noble who is particularly prominent, distinguished, or widely recognized in some notable way.
-
C.
usedByNobleFamily
Indicates that something is employed, possessed, or otherwise utilized by a noble family.
-
D.
hasNoble
Indicates that one entity possesses or is associated with a noble title, status, or noble individual.
-
E.
associatedNobleFamily
chosen
Indicates a relationship where an entity is linked or connected to a particular noble family, typically by heritage, allegiance, or formal association.
- 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_69c687ed8a9c81908bb671717cb192ef |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6bdb88cc881908f35648c15a7dc85 |
completed | March 27, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69c6ad007c1c8190af425f51011c7ad1 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:58 p.m.