Triple
T22012216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lavender Brown |
E543604
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Jessie Cave |
—
|
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: Jessie Cave | Statement: [Lavender Brown, portrayedBy, Jessie Cave]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jessie Cave Context triple: [Lavender Brown, portrayedBy, Jessie Cave]
-
A.
Jessie Cave
chosen
Jessie Cave is a British actress, comedian, and illustrator best known for playing Lavender Brown in the Harry Potter film series.
-
B.
Jessie Holland
Jessie Holland was the wife of prominent 19th-century English architect George Edmund Street and a member of Victorian Britain's cultural milieu.
-
C.
Jessie Henderson
Jessie Henderson is a film producer known for her work on contemporary comedies and romantic comedies, including the holiday film "Last Christmas."
-
D.
Jessie Deighan
Jessie Deighan is a character from the action film "Cliffhanger," serving as a close ally and love interest of mountain climber Gabe Walker.
-
E.
Alexandra Cave
Alexandra Cave is a limestone show cave in South Australia's Naracoorte Caves system, noted for its impressive speleothems and accessible guided tours.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a520bc8190865f525a87255fb2 |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:22 p.m.