Triple
T10367938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dirty Pretty Things |
E244302
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object | Audrey Tautou |
E72816
|
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: Audrey Tautou | Statement: [Dirty Pretty Things, starredActor, Audrey Tautou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Audrey Tautou Context triple: [Dirty Pretty Things, starredActor, Audrey Tautou]
-
A.
Audrey Tautou
chosen
Audrey Tautou is a French actress best known internationally for her lead role in the film "Amélie" and for starring in several major French and Hollywood productions.
-
B.
Juliette Binoche
Juliette Binoche is an acclaimed French actress known for her nuanced performances in international cinema and her Academy Award-winning role in "The English Patient."
-
C.
Laetitia Casta
Laetitia Casta is a French supermodel and actress known for her work with major fashion houses and her roles in European cinema.
-
D.
Nelly Auteuil
Nelly Auteuil is the daughter of French actor and filmmaker Daniel Auteuil.
-
E.
Julie Delpy
Julie Delpy is a French-American actress, filmmaker, and screenwriter best known for co-writing and starring in Richard Linklater’s "Before" trilogy.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e97106448190a075948e63184f47 |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7fb8e96e081908282bb0f82719abe |
completed | April 9, 2026, 7:18 p.m. |
Created at: April 6, 2026, noon