Triple
T24029887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alan IV, Duke of Brittany |
E595069
|
entity |
| Predicate | motherHeldTitle |
P20541
|
FINISHED |
| Object | Duchess of Brittany in her own right |
—
|
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: Duchess of Brittany in her own right | Statement: [Alan IV, Duke of Brittany, motherHeldTitle, Duchess of Brittany in her own right]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motherHeldTitle Context triple: [Alan IV, Duke of Brittany, motherHeldTitle, Duchess of Brittany in her own right]
-
A.
motherTitle
Indicates the formal title or honorific associated with a person's mother.
-
B.
heldTitleByRightOfMother
chosen
Indicates that an individual holds a title or rank derived through their mother’s hereditary rights or lineage.
-
C.
titleHolderMother
Indicates that the subject is the mother of the current or specified holder of a particular title.
-
D.
motherInLawOfTitleHolder
Indicates that one person is the mother-in-law of the title holder, i.e., the mother of the title holder’s spouse.
-
E.
motherWas
Indicates that one entity was the mother (biological or adoptive) of another entity at some time in the past.
- 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_69e288bf45f08190a1b6ed8cd0b9e86b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d76fbedc8190a2f936729cb69993 |
completed | April 29, 2026, 10:03 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:55 p.m.