Triple
T23788313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeff Tarpley |
E588017
|
entity |
| Predicate | sharesCustodyOf |
P37105
|
FINISHED |
| Object | Jeffrey Charles Tarpley Jr. |
—
|
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: Jeffrey Charles Tarpley Jr. | Statement: [Jeff Tarpley, sharesCustodyOf, Jeffrey Charles Tarpley Jr.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesCustodyOf Context triple: [Jeff Tarpley, sharesCustodyOf, Jeffrey Charles Tarpley Jr.]
-
A.
sharesCustodyWith
chosen
Indicates that two or more parties jointly hold legal responsibility and decision-making authority for the care and upbringing of the same dependent, typically a child.
-
B.
sharesOwnershipWith
Indicates that two or more entities jointly hold ownership rights or stakes in the same asset, resource, or organization.
-
C.
custody
Indicates having legal responsibility and authority over the care and control of another entity, typically a child or dependent.
-
D.
sharesChildrenWith
Indicates that two entities are co-parents, having one or more children in common.
-
E.
sharesDivisionWith
Indicates that two entities belong to or operate within the same organizational division.
- 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_69e2490f4ad48190b690878eec3596c6 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c6332cb48190aa45ca6d8d98ed08 |
completed | April 29, 2026, 8:49 a.m. |
| PD | Predicate disambiguation | batch_69f155fe300481909bd617443228df65 |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:17 p.m.