Triple
T15578648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosaic (TV series) |
E374434
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Jennifer Ferrin |
E1116240
|
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: Jennifer Ferrin | Statement: [Mosaic (TV series), stars, Jennifer Ferrin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jennifer Ferrin Context triple: [Mosaic (TV series), stars, Jennifer Ferrin]
-
A.
Jennifer Ferrin
chosen
Jennifer Ferrin is an American actress best known for her work in television dramas and series such as "The Cape" and "As the World Turns."
-
B.
Emily Greer
Emily Greer is a notable individual recognized as a prominent bearer of the surname Greer.
-
C.
Teresa Nielsen Hayden
Teresa Nielsen Hayden is an American science fiction editor, writer, and influential blogger known for her work at Tor Books and her role in online fan communities.
-
D.
Elizabeth Kern
Elizabeth Kern was the wife of renowned American jazz clarinetist and bandleader Artie Shaw.
-
E.
Sandra Hunt
Sandra Hunt is best known as the wife of legendary Los Angeles Dodgers broadcaster Vin Scully.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e24064c8190b132c3092877fbfa |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff7563674c81908b035a7672b2827d |
completed | May 9, 2026, 5:56 p.m. |
Created at: April 10, 2026, 4:11 a.m.