Triple
T16108079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Susan Lewis |
E390794
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Sherry Stringfield |
—
|
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: Sherry Stringfield | Statement: [Dr. Susan Lewis, portrayedBy, Sherry Stringfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sherry Stringfield Context triple: [Dr. Susan Lewis, portrayedBy, Sherry Stringfield]
-
A.
Sherry Stringfield
chosen
Sherry Stringfield is an American actress best known for her role as Dr. Susan Lewis on the television medical drama "ER."
-
B.
Sherry Cervi
Sherry Cervi is a renowned American barrel racer and multiple-time world champion in professional rodeo.
-
C.
Sherry Dyson
Sherry Dyson is an American mathematics educator best known as the former wife of entrepreneur and motivational speaker Chris Gardner, whose life inspired the film "The Pursuit of Happyness."
-
D.
Diane Sherry
Diane Sherry is an actress best known for playing Lana Lang in the 1978 superhero film "Superman."
-
E.
Cheryl Johnson
Cheryl Johnson is the wife of American sportscaster Ernie Johnson Jr., known for her long-standing support of his broadcasting career and their family.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e20165aa9c81908c5358cca2b0d0fe |
completed | April 17, 2026, 9:46 a.m. |
Created at: April 10, 2026, 5 a.m.