Triple
T20472926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ambrosius Flume |
E502237
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mrs Flume |
—
|
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: Mrs Flume | Statement: [Ambrosius Flume, spouse, Mrs Flume]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mrs Flume Context triple: [Ambrosius Flume, spouse, Mrs Flume]
-
A.
Mrs Flume
chosen
Mrs Flume is a witch in the Harry Potter series who co-owns and runs Honeydukes, the popular sweet shop in Hogsmeade.
-
B.
Sylvia Flote
Sylvia Flote is an actress who appeared in the critically acclaimed psychological drama film "Tár."
-
C.
Bess Flowers
Bess Flowers was a prolific American character actress best known as the "Queen of the Hollywood Extras" for her hundreds of uncredited appearances in classic films from the 1920s through the 1960s.
-
D.
Florrie Palmer
Florrie Palmer is a British songwriter best known for penning Sheena Easton’s hit single "Morning Train (Nine to Five)."
-
E.
Flora Drew
Flora Drew is a British translator and editor best known for her work translating and promoting the writings of Chinese author Ma Jian.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69962d810819091bb13fe73250e24 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.