Triple
T17921061
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adriaane Pielou |
E448066
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Lucy Boynton |
—
|
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: Lucy Boynton | Statement: [Adriaane Pielou, hasChild, Lucy Boynton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lucy Boynton Context triple: [Adriaane Pielou, hasChild, Lucy Boynton]
-
A.
Lucy Boynton
chosen
Lucy Boynton is a British-American actress known for her roles in films such as "Bohemian Rhapsody" and "Sing Street," as well as various television dramas.
-
B.
Kate O’Flynn
Kate O’Flynn is a British actress known for her work in film, television, and theatre, including a role in the romantic comedy sequel "Bridget Jones’s Baby."
-
C.
Lily Houghton
Lily Houghton is a fictional, adventurous British botanist and explorer from the film "Jungle Cruise."
-
D.
Danielle Macdonald
Danielle Macdonald is an Australian actress known for her breakout roles in films such as "Patti Cake$," "Dumplin'," and the drama "Skin."
-
E.
Maria Riva
Maria Riva is a German-American actress and author best known as the daughter and biographer of film legend Marlene Dietrich.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30a11748190be41361d108aee58 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.