Triple
T22078039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bonnie Wright |
E545572
|
entity |
| Predicate | hasSibling |
P363
|
FINISHED |
| Object | Lewis Wright |
—
|
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: Lewis Wright | Statement: [Bonnie Wright, hasSibling, Lewis Wright]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lewis Wright Context triple: [Bonnie Wright, hasSibling, Lewis Wright]
-
A.
Lewis Wright
chosen
Lewis Wright is a sibling of English actress and director Bonnie Wright, who is best known for playing Ginny Weasley in the Harry Potter film series.
-
B.
Austin Wright
Austin Wright was an American novelist and academic best known for his psychological thriller "Tony and Susan," which was later adapted into the film "Nocturnal Animals."
-
C.
Ray Wright
Ray Wright is a screenwriter known for his work on the film "Case 39" and other genre-focused screenplays.
-
D.
Sam Wright
Sam Wright is an individual known primarily as a relative of George Wright.
-
E.
John Michael Wright
John Michael Wright is the son of Laura Wright.
- 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_69e11e3523488190badd54b5d580c00d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128b38844819084526372fa6c6e35 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.