Triple
T22840857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wanderlust |
E566073
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Zawe Ashton |
—
|
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: Zawe Ashton | Statement: [Wanderlust, starring, Zawe Ashton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zawe Ashton Context triple: [Wanderlust, starring, Zawe Ashton]
-
A.
Zawe Ashton
chosen
Zawe Ashton is a British actress, playwright, and director known for her work in film, television, and theatre, including roles in projects like "Fresh Meat" and "Velvet Buzzsaw."
-
B.
Daniela Denby-Ashe
Daniela Denby-Ashe is a British actress best known for her roles in television series such as "My Family," "EastEnders," and the period drama "North & South."
-
C.
Rachel Whittle
Rachel Whittle is an actress known for her role in the 2015 psychological thriller film "The Shelter."
-
D.
Tamara Goff
Tamara Goff is known primarily as the spouse of Australian-born screenwriter Ivan Goff, co-creator of the television series "Charlie's Angels."
-
E.
Jennifer Ashton
Jennifer Ashton is an American physician and television medical correspondent best known as the chief medical correspondent for ABC News.
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e83fa48819084568264ef45c833 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.