Triple
T17632202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. and Mrs. Bridge (film) |
E430004
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Katherine Wenning |
—
|
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: Katherine Wenning | Statement: [Mr. and Mrs. Bridge (film), editor, Katherine Wenning]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Katherine Wenning Context triple: [Mr. and Mrs. Bridge (film), editor, Katherine Wenning]
-
A.
Katherine Wenning
chosen
Katherine Wenning is an editor known for her work on the film "Maurice."
-
B.
Katherine Hewitt
Katherine Hewitt was one of the accused women in the 1612 Pendle witch trials in Lancashire, England, a notorious early modern witchcraft prosecution.
-
C.
Katherine Hudson
Katherine Hudson is the mother of Richard Hudson.
-
D.
Katherine Hudson
Katherine Hudson is the child of John Hudson, about whom no widely known public information is available.
-
E.
Katherine Hudson
Katherine Hudson is the mother of American actor Oliver Hudson and a member of the Hudson family connected to the entertainment industry.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dc276b48190923f1869ebfe4400 |
completed | April 19, 2026, 5:53 a.m. |
Created at: April 10, 2026, 5:52 a.m.