Triple
T18330302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarana Burke |
E439119
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Burke |
—
|
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: Burke | Statement: [Tarana Burke, familyName, Burke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burke Context triple: [Tarana Burke, familyName, Burke]
-
A.
Burke
Burke is a suburban community in Fairfax County, Northern Virginia, known for its residential neighborhoods, parks, and proximity to Washington, D.C.
-
B.
Burke
Burke is a town located in Dane County, Wisconsin, known as a suburban community near the city of Madison.
-
C.
Burke
chosen
Burke is a common Irish-origin surname borne by numerous notable figures across politics, the arts, and public life.
-
D.
Burke’s
Burke’s was a regional American department store chain that later became part of the Federated Department Stores retail portfolio.
-
E.
Trevelyan
Trevelyan is an English surname historically associated with several notable British families, politicians, and literary figures.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ec900808190bc4468270e0957c1 |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:36 a.m.