Triple
T23381575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apostle Jude |
E593761
|
entity |
| Predicate | possibleRelativeOf |
P42547
|
FINISHED |
| Object | Jesus |
—
|
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: Jesus | Statement: [Apostle Jude, possibleRelativeOf, Jesus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: possibleRelativeOf Context triple: [Apostle Jude, possibleRelativeOf, Jesus]
-
A.
possibleRelative
chosen
Indicates a relationship where one entity may be related to another by family or kinship, but the exact nature of the relationship is uncertain or not fully established.
-
B.
mayRelateTo
Indicates a possible, but not certain, relationship or association between two entities.
-
C.
appointedRelative
Indicates that one entity has formally assigned or designated another entity, who is a relative, to a specific role, position, or responsibility.
-
D.
possibleDescendant
Indicates that one entity may be a descendant of another, without asserting that the descendant relationship is certain.
-
E.
relationshipToRelative
Indicates the specific familial connection or kinship role that one person has in relation to a particular relative.
- 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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b7eff48190be126df2211b4c85 |
completed | April 29, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69f061dde2e481908308952f9c0d3c2e |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:34 p.m.