Triple
T15832424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ursula Burns |
E383903
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Burns |
E156468
|
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: Burns | Statement: [Ursula Burns, familyName, Burns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burns Context triple: [Ursula Burns, familyName, Burns]
-
A.
Burns
chosen
Burns is a common Scottish surname most famously associated with the poet Robert Burns.
-
B.
Burns
Burns is an electronic music producer and DJ known for his work in dance and pop music, including collaborations with major artists.
-
C.
Burns
Burns is a small city in Harney County, eastern Oregon, known as a remote high-desert community and regional service center for the surrounding ranching and natural resource areas.
-
D.
Burned
Burned is a mystery novel by American author Carol Higgins Clark, featuring her recurring sleuth Regan Reilly in a suspenseful, lighthearted whodunit.
-
E.
Burn
Burn is the first name of Burn Gorman, a British-American actor known for roles in productions such as "Torchwood," "Game of Thrones," and "Pacific Rim."
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e11e653e388190a4696cdb22546715 |
completed | April 16, 2026, 5:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff999f9ccc8190bc859c2b78a16baf |
completed | May 9, 2026, 8:31 p.m. |
Created at: April 10, 2026, 4:49 a.m.