Triple
T13189510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christina Bruce |
E313946
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | John Bruce |
E330746
|
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: John Bruce | Statement: [Christina Bruce, relative, John Bruce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Bruce Context triple: [Christina Bruce, relative, John Bruce]
-
A.
John Bruce
chosen
John Bruce was the short-lived son and heir of Robert the Bruce, King of Scots, and his queen consort Elizabeth de Burgh.
-
B.
John Buchanan
John Buchanan is a clergyman who formerly served as a bishop in the Episcopal Church, notably within the Diocese of Virginia.
-
C.
James Gillespie
James Gillespie was a 19th-century Texas figure, likely a politician or military leader, honored as the namesake of Gillespie County.
-
D.
Robert Bruce Ford
Robert Bruce Ford was a controversial Canadian politician who served as the 64th mayor of Toronto from 2010 to 2014, gaining international notoriety for his populist style and substance abuse scandals.
-
E.
John Stewart Bryan
John Stewart Bryan was an American newspaper publisher and educator who served as president and later chancellor of the College of William & Mary in the early 20th century.
- 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c4d60688190b34e65bbb5d4c152 |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7546b9ae081909f97fc4a06b8f927 |
completed | May 3, 2026, 1:58 p.m. |
Created at: April 9, 2026, 9:15 p.m.