Triple
T25293799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bellamy Young |
E634160
|
entity |
| Predicate | Mellie GrantIs |
P69227
|
FINISHED |
| Object | First Lady of the United States on "Scandal" |
—
|
LITERAL FINISHED |
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: First Lady of the United States on "Scandal" | Statement: [Bellamy Young, Mellie GrantIs, First Lady of the United States on "Scandal"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Mellie GrantIs Context triple: [Bellamy Young, Mellie GrantIs, First Lady of the United States on "Scandal"]
-
A.
HethIs
chosen
Indicates that one entity is identified as or equated with another entity, expressing a basic “is” or “being” relationship between them.
-
B.
isMarilyn
Indicates that the subject is (or is being identified as) Marilyn.
-
C.
fiancéePortrayedBy
Indicates that a character’s fiancée is depicted or played by a specific actor or performer.
-
D.
isEldestSisterOf
Indicates that one person is the oldest female sibling in relation to another person.
-
E.
granteeFullName
Indicates the complete personal name of the entity that receives a grant or is designated as the grantee.
- 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_69e75a9503d48190b80a005c6af0cb50 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48fd007388190a7d80ea457119072 |
completed | May 1, 2026, 11:34 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
Created at: April 21, 2026, 1:22 p.m.