Triple
T23052677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winnie Cooper |
E574062
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Carol Black |
—
|
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: Carol Black | Statement: [Winnie Cooper, creator, Carol Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Black Context triple: [Winnie Cooper, creator, Carol Black]
-
A.
Carol Black
chosen
Carol Black is an American television writer, producer, and director best known for co-creating the acclaimed coming-of-age series "The Wonder Years."
-
B.
Anne Todd
Anne Todd was a British film actress active in the mid-20th century, known for her roles in adventure and drama films.
-
C.
Moira Harris
Moira Harris is an American actress known for her film, television, and stage work, and for her long-time marriage to actor and director Gary Sinise.
-
D.
Susie Cave
Susie Cave is a British fashion designer, former model, and founder of the cult label The Vampire’s Wife, as well as the wife of musician Nick Cave.
-
E.
Margaret Forster
Margaret Forster was a British novelist, biographer, and critic known for works such as "Georgy Girl" and her acclaimed literary biographies.
- 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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1867dfac48190bf300f85d2907854 |
completed | April 29, 2026, 4:18 a.m. |
Created at: April 17, 2026, 3:54 p.m.