Triple
T12904204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Toombs |
E308689
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Martha Julianna DuBose |
E977631
|
NE FINISHED |
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: Martha Julianna DuBose | Statement: [Robert Toombs, spouse, Martha Julianna DuBose]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martha Julianna DuBose Context triple: [Robert Toombs, spouse, Martha Julianna DuBose]
-
A.
Martha Julianna DuBose
chosen
Martha Julianna DuBose was the wife of prominent 19th-century American politician and Confederate leader Robert Toombs.
-
B.
Marion Brown
Marion Brown was an American jazz alto saxophonist and composer associated with the avant-garde and free jazz movements of the 1960s and beyond.
-
C.
Elouise Sidwell
Elouise Sidwell was the wife of American composer and television theme music writer Earle Hagen.
-
D.
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.
-
E.
Anna Boyd
Anna Boyd is a character associated with Rachel Watson, likely appearing as one of her allies in the psychological thriller novel and film "The Girl on the Train."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971831bd48190b0ecd13e7181bbc6 |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a563a84c8190a75d830653661518 |
completed | May 3, 2026, 1:31 a.m. |
Created at: April 9, 2026, 5:40 p.m.