Triple
T23477598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Numb3rs |
E570307
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Sophina Brown |
—
|
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: Sophina Brown | Statement: [Numb3rs, stars, Sophina Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sophina Brown Context triple: [Numb3rs, stars, Sophina Brown]
-
A.
Sophina Brown
chosen
Sophina Brown is an American actress best known for her television roles on series such as Shark and Numb3rs.
-
B.
Leola Brown
Leola Brown was the wife of Oliver Brown, the named plaintiff in the landmark U.S. Supreme Court school desegregation case Brown v. Board of Education.
-
C.
Lovina Smith
Lovina Smith was a 19th-century Latter-day Saint woman and daughter of early LDS leader Hyrum Smith.
-
D.
Willa Brown
Willa Brown was a pioneering African American aviator, flight instructor, and civil rights advocate who became the first Black woman in the United States to earn both a pilot’s license and a commercial pilot’s license.
-
E.
Clarissa Brown
Clarissa Brown was the wife of American explorer and soldier Zebulon Pike, known for her connection to his early 19th-century expeditions and military career.
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:02 p.m.