Triple
T23999170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeffrey Epstein |
E594193
|
entity |
| Predicate | notableAllegedAssociate |
P120587
|
FINISHED |
| Object | Ghislaine Maxwell |
—
|
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: Ghislaine Maxwell | Statement: [Jeffrey Epstein, notableAllegedAssociate, Ghislaine Maxwell]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableAllegedAssociate Context triple: [Jeffrey Epstein, notableAllegedAssociate, Ghislaine Maxwell]
-
A.
notablyAssociatedWith
Indicates that one entity is prominently or distinctively connected with another in a way that is especially noteworthy or remarkable.
-
B.
notoriouslyAssociatedWith
Indicates a widely recognized and often negative or infamous association between one entity and another.
-
C.
hasAllegedRelationshipWith
chosen
Indicates a claimed or suspected relationship between two entities that is not confirmed as factual.
-
D.
allegedAgentOf
Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
-
E.
notableAdversary
Indicates that one entity is recognized as a significant or prominent opponent or rival of another entity.
- 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_69e288b9ecf08190b8c94a278f5674fe |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d460b07881908ad11c03890ec1de |
completed | April 29, 2026, 9:50 a.m. |
| PD | Predicate disambiguation | batch_69f1615994c48190a5de95d3f7e5cd0a |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:39 p.m.