Triple
T21480954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marnie Piper |
E529990
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Kimberly J. Brown |
—
|
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: Kimberly J. Brown | Statement: [Marnie Piper, portrayedBy, Kimberly J. Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kimberly J. Brown Context triple: [Marnie Piper, portrayedBy, Kimberly J. Brown]
-
A.
Kimberly J. Brown
chosen
Kimberly J. Brown is an American actress best known for playing Marnie Piper in Disney Channel’s Halloweentown film series.
-
B.
Kimberly Woodard
Kimberly Woodard is a television producer best known for her executive production work on the live law-enforcement reality series "Live PD."
-
C.
Adrienne A. Jones
Adrienne A. Jones is an American politician who serves as the Speaker of the Maryland House of Delegates and is the first African American and first woman to hold that position.
-
D.
Monika M. Richardson
Monika M. Richardson is the wife of American voice actor Kevin Michael Richardson.
-
E.
Tracey E. Edmonds
Tracey E. Edmonds is an American television and film producer and businesswoman known for her work in entertainment and media entrepreneurship.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea338f988190a3044f8d02a567fe |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.