Triple
T19828966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Parish |
E476404
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sarah Parish |
—
|
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: Sarah Parish | Statement: [Sarah Parish, name, Sarah Parish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Parish Context triple: [Sarah Parish, name, Sarah Parish]
-
A.
Sarah Parish
chosen
Sarah Parish is an English actress known for her extensive work in British television drama and comedy, including prominent roles in series such as "Cutting It," "Mistresses," and "Broadchurch."
-
B.
Elizabeth Killian
Elizabeth Killian is the namesake of an endowed economics professorship at the Massachusetts Institute of Technology.
-
C.
Lanie Parish
Lanie Parish is a sharp-witted medical examiner and close friend of Kate Beckett on the crime-comedy TV series "Castle."
-
D.
Charlotte Shanks
Charlotte Shanks is the wife of American actor Tom Skerritt.
-
E.
Kim Gannon
Kim Gannon was an American songwriter best known for penning the lyrics to several popular mid-20th-century songs, including the holiday standard "I'll Be Home for Christmas."
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656ccd3748190adeaed9a431f8979 |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.