Triple
T22223776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norma Deloris Egstrom |
E549279
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Brad Dexter |
—
|
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: Brad Dexter | Statement: [Norma Deloris Egstrom, spouse, Brad Dexter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad Dexter Context triple: [Norma Deloris Egstrom, spouse, Brad Dexter]
-
A.
Brad Dexter
chosen
Brad Dexter was an American character actor and film producer best known for his role as one of the gunfighters in the classic Western film "The Magnificent Seven."
-
B.
Chris Van Dahl
Chris Van Dahl is an American rock singer best known as a former lead vocalist of the hard rock band L.A. Guns.
-
C.
Ben Browder
Ben Browder is an American actor best known for his leading roles in the science fiction television series Farscape and Stargate SG-1.
-
D.
D.B. Sweeney
D.B. Sweeney is an American actor known for his roles in films like "The Cutting Edge" and "Eight Men Out" as well as numerous television appearances.
-
E.
Jeffrey Dean
Jeffrey Dean is a prominent American computer scientist and software engineer best known for his influential work on large-scale distributed systems and infrastructure at Google.
- 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_69e11e403d6481909a94d0aaf157f6ef |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b92b79c8190a8a4d33591abd763 |
completed | April 28, 2026, 9:50 p.m. |
Created at: April 16, 2026, 8:37 p.m.