Triple
T22660041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | STS-28 |
E559636
|
entity |
| Predicate | missionSpecialist |
P21471
|
FINISHED |
| Object | Mark N. 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: Mark N. Brown | Statement: [STS-28, missionSpecialist, Mark N. Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark N. Brown Context triple: [STS-28, missionSpecialist, Mark N. Brown]
-
A.
Mark N. Brown
chosen
Mark N. Brown is a former NASA astronaut and U.S. Air Force officer who flew on two Space Shuttle missions, including STS-48.
-
B.
David R. Brown
David R. Brown was an architect known for designing New Haven City Hall in New Haven, Connecticut.
-
C.
Wesley A. Brown
Wesley A. Brown was the first African American graduate of the United States Naval Academy and a pioneering U.S. Navy officer.
-
D.
David H. Brown
David H. Brown was one of the defendants tried alongside Dr. Ossian Sweet in the landmark 1925 Detroit case involving racial tensions, self-defense, and housing segregation.
-
E.
Jeffrey G. Brown
Jeffrey G. Brown is a television and film producer known for his executive production work on projects such as the 2004 miniseries adaptation of Stephen King’s "Salem’s Lot."
- 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_69e2454a158c819093b8e35f5045efb6 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1765edf88819086c28525e3c73758 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 3:07 p.m.