Triple
T17890569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ella Craig |
E447303
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ella Craig |
—
|
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: Ella Craig | Statement: [Ella Craig, name, Ella Craig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ella Craig Context triple: [Ella Craig, name, Ella Craig]
-
A.
Ella Craig
chosen
Ella Craig is a British-American actress and model best known as the daughter of James Bond star Daniel Craig.
-
B.
Clare Foley
Clare Foley is an American actress known for her roles in film and television, including appearances in projects like the boxing drama "Southpaw" and the TV series "Gotham."
-
C.
Sharron Macready
Sharron Macready is a fictional British secret agent and one of the three enhanced protagonists in the 1960s science fiction television series "The Champions."
-
D.
Betty McCutcheon
Betty McCutcheon is a fictional character from the crime film "Deep Cover."
-
E.
Caroline Abbott
Caroline Abbott is a central character in E.M. Forster’s novel "Where Angels Fear to Tread," whose moral earnestness and cultural naivety drive much of the story’s conflict.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7948888190b59ddc7061d13e84 |
completed | April 19, 2026, 9:16 a.m. |
Created at: April 10, 2026, 10:18 a.m.