Triple
T33468692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ayesha Shand |
E857126
|
entity |
| Predicate | hasPaternalAunt |
P147360
|
FINISHED |
| Object | Camilla, Queen Consort |
—
|
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: Camilla, Queen Consort | Statement: [Ayesha Shand, hasPaternalAunt, Camilla, Queen Consort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPaternalAunt Context triple: [Ayesha Shand, hasPaternalAunt, Camilla, Queen Consort]
-
A.
hasAunt
Indicates that one entity is the aunt of another, typically meaning a sister (or sister-in-law) of a parent of that entity.
-
B.
maternalAuntOrUncle
Indicates that one person is the sibling of another person's mother, regardless of the sibling's gender.
-
C.
paternalAuntByMarriage
chosen
Indicates that one person is the wife of another person’s paternal uncle (their father’s brother).
-
D.
hasPaternalGrandparent
Indicates that one entity is the paternal grandparent (father’s parent) of another entity.
-
E.
uncleOrAuntOf
Indicates that one person is the uncle or aunt of another person, typically as the sibling (or sibling-in-law) of the other person’s parent.
- 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: May 1, 2026, 1:37 a.m.