Triple
T21345680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Lynch |
E526328
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Evanna Lynch |
—
|
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: Evanna Lynch | Statement: [Patrick Lynch, sibling, Evanna Lynch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evanna Lynch Context triple: [Patrick Lynch, sibling, Evanna Lynch]
-
A.
Evanna Lynch
chosen
Evanna Lynch is an Irish actress best known for playing Luna Lovegood in the Harry Potter film series.
-
B.
Emma Watson
Emma Watson is a British actress and activist best known for playing Hermione Granger in the Harry Potter film series and for her advocacy on gender equality.
-
C.
Bonnie Wright
Bonnie Wright is an English actress and filmmaker best known for playing Ginny Weasley in the Harry Potter film series.
-
D.
Hermione Baddeley
Hermione Baddeley was an English character actress known for her sharp-tongued, memorable supporting roles in British cinema and later in Hollywood films and television.
-
E.
Rebecca Gleeson
Rebecca Gleeson is an Australian publicist best known as the wife of actor Eric Bana.
- 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_69e0b51cd5cc81909ac1187971e8a8ad |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8a854e8ec81909efd41c1e959cc61 |
completed | April 22, 2026, 10:52 a.m. |
Created at: April 16, 2026, 4:54 p.m.