Triple
T9936502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beverly Marsh |
E192771
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Emily Perkins |
E742813
|
NE 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: Emily Perkins | Statement: [Beverly Marsh, portrayedBy, Emily Perkins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emily Perkins Context triple: [Beverly Marsh, portrayedBy, Emily Perkins]
-
A.
Emily Perkins
chosen
Emily Perkins is a Canadian actress best known for her roles in the horror film "Ginger Snaps" and the television miniseries adaptation of Stephen King’s "It."
-
B.
Zoe Perkins
Zoe Perkins is a daughter of renowned American book editor Maxwell Perkins, who was famous for working with authors like F. Scott Fitzgerald and Ernest Hemingway.
-
C.
Jane Perkins
Jane Perkins is a contemporary artist known for creating intricate portraits and artworks using found objects and recycled materials.
-
D.
Emily Procter
Emily Procter is an American actress best known for her role as ballistics expert Calleigh Duquesne on the television series CSI: Miami.
-
E.
Jennifer Winkley
Jennifer Winkley is known as the former spouse of acclaimed American novelist Cormac McCarthy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e3bfa88190a88f20f2687a2583 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3000b21088190aa3ebb2ccbce9a6e |
completed | April 6, 2026, 12:36 a.m. |
Created at: March 30, 2026, 8:44 p.m.