Triple
T2651310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burn Gorman |
E53903
|
entity |
| Predicate | hasSpouse |
P13
|
FINISHED |
| Object | Sarah Beard |
E68519
|
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: Sarah Beard | Statement: [Burn Gorman, hasSpouse, Sarah Beard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Beard Context triple: [Burn Gorman, hasSpouse, Sarah Beard]
-
A.
Sarah Beard
chosen
Sarah Beard is known as the wife of British-American actor and musician Burn Gorman.
-
B.
Cornelia Bell
Cornelia Bell was the wife of William Paterson, a Founding Father and early U.S. Supreme Court Associate Justice.
-
C.
Maria Franklin
Maria Franklin was the first wife of DeWitt Clinton, a prominent early 19th-century New York politician and governor.
-
D.
Laura Florence Calvert
Laura Florence Calvert was the wife of American architect Henry Bacon, best known for designing the Lincoln Memorial in Washington, D.C.
-
E.
Beatrice Durham
Beatrice Durham was the wife of pioneering British geneticist William Bateson and a supportive figure in his personal and scientific life.
- 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_69ab495e192081909c77b622e8e7e15a |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd93071248190820197936e3167f7 |
completed | March 7, 2026, 7:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af98cc2d9881908556b915a1870c02 |
completed | March 10, 2026, 4:06 a.m. |
Created at: March 6, 2026, 9:53 p.m.