Triple
T27267767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viscount Boyle |
E687952
|
entity |
| Predicate | relatedFamilyTitle |
P100487
|
FINISHED |
| Object | Earl of Cork |
—
|
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: Earl of Cork | Statement: [Viscount Boyle, relatedFamilyTitle, Earl of Cork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedFamilyTitle Context triple: [Viscount Boyle, relatedFamilyTitle, Earl of Cork]
-
A.
linkedFamilyTitle
Indicates that one entity is associated with another through a family-related title or role (such as parent, sibling, or spouse).
-
B.
subjectFamilyRelation
Indicates that there is a familial relationship of some kind between the subject entity and another entity.
-
C.
linkedTitleFamily
chosen
Indicates that one title is associated with or belongs to the same family or grouping of related titles as another.
-
D.
notableFamilyMemberTitle
Indicates that a person has a family member whose title or designation is notable or significant.
-
E.
spouseRelative
Indicates that one person is related to another through the marriage of at least one of them (e.g., in-laws or relatives by marriage).
- 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_69ef3557abc481908bf3c146f0f3356a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ff4fc6077c8190b8fd9b43fcfde986 |
completed | May 9, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69ff4e61fb648190a72f7918961ece9c |
completed | May 9, 2026, 3:10 p.m. |
Created at: April 27, 2026, 10:57 a.m.