Triple
T26556045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abel Meeropol |
E671809
|
entity |
| Predicate | adoptedChildrenOf |
P40227
|
FINISHED |
| Object | Julius Rosenberg |
—
|
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: Julius Rosenberg | Statement: [Abel Meeropol, adoptedChildrenOf, Julius Rosenberg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adoptedChildrenOf Context triple: [Abel Meeropol, adoptedChildrenOf, Julius Rosenberg]
-
A.
adoptedChildren
chosen
Indicates that one entity has legally taken another entity as their child through adoption.
-
B.
adoptedChildrenFrom
Indicates a relationship where one entity has legally adopted children originating from another entity (such as a person, couple, or organization).
-
C.
childrenWith
Indicates that two or more entities share one or more children together as parents or guardians.
-
D.
numberOfAdoptedChildren
Indicates the count of children that an entity has legally adopted.
-
E.
adoptedUnder
Indicates that something has been formally accepted, implemented, or brought into effect according to a specified rule, procedure, or authority.
- 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_69eeb32163f08190af5f81282738e27a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b3a8ae0819090189fbd8eb19f2f |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 1:50 a.m.