Triple
T17655156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roberts Scott Blossom |
E429600
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Beverly Schmidt Blossom |
—
|
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: Beverly Schmidt Blossom | Statement: [Roberts Scott Blossom, spouse, Beverly Schmidt Blossom]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beverly Schmidt Blossom Context triple: [Roberts Scott Blossom, spouse, Beverly Schmidt Blossom]
-
A.
Beverly Schmidt
chosen
Beverly Schmidt was the wife of American character actor and poet Roberts Blossom.
-
B.
Betsy Jane Becker
Betsy Jane Becker is known as the wife of American actor and producer Matthew Salinger, son of author J.D. Salinger.
-
C.
Vivian Sibold
Vivian Sibold is a German interior designer and entrepreneur best known as the wife of former Formula 1 World Champion Nico Rosberg.
-
D.
Joyce Rudolph
Joyce Rudolph is known as the spouse of American film director and screenwriter Alan Rudolph.
-
E.
Arlene Sanford
Arlene Sanford is an American television and film director known for her work on numerous popular TV series and made-for-TV movies.
- 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_69d889e2c2608190b762e76d9b2262f1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46e3fc6e8819080098a3cd0183811 |
completed | April 19, 2026, 5:55 a.m. |
Created at: April 10, 2026, 6:06 a.m.