Triple
T34646003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth de Ferrers |
E889695
|
entity |
| Predicate | spousePatronymic |
P7966
|
FINISHED |
| Object | ap Gruffudd |
—
|
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: ap Gruffudd | Statement: [Elizabeth de Ferrers, spousePatronymic, ap Gruffudd]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spousePatronymic Context triple: [Elizabeth de Ferrers, spousePatronymic, ap Gruffudd]
-
A.
spouseFamilyName
Indicates that the object is the family name (surname) shared by or associated with a person's spouse.
-
B.
patronymicOrMatronymic
Indicates that one entity’s name is derived from the father’s or mother’s name, expressing a parent-based naming relationship between the two entities.
-
C.
spouseGivenName
Indicates that the value is the given (first) name of a person's spouse in the relationship.
-
D.
patronymicName
chosen
Indicates that one entity’s name is derived from or based on the given name of a parent or ancestor, typically the father.
-
E.
spouse name
Indicates that one entity is the legally recognized husband or wife of the other, specifying the partner’s name in a marital relationship.
- 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_69f349d825c88190bfc6170ac9281260 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fe08d2b2e48190ac7be6d62d4a44a3 |
completed | May 8, 2026, 4:01 p.m. |
| PD | Predicate disambiguation | batch_69fe06cd3af08190ae25de0dc0cdd573 |
completed | May 8, 2026, 3:52 p.m. |
Created at: May 1, 2026, 2:04 a.m.