Triple
T4450272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarana Burke |
E97590
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Tarana Burke |
E97590
|
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: Tarana Burke | Statement: [Tarana Burke, name, Tarana Burke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tarana Burke Context triple: [Tarana Burke, name, Tarana Burke]
-
A.
Tarana Burke
chosen
Tarana Burke is an American civil rights activist best known for originating the "Me Too" movement to support survivors of sexual violence.
-
B.
Mandisa Glover
Mandisa Glover is the daughter of acclaimed American actor and activist Danny Glover.
-
C.
Rebecca Walker
Rebecca Walker is an American writer, feminist, and cultural critic known for her work on third-wave feminism and issues of race, gender, and identity.
-
D.
Solána Imani Rowe
Solána Imani Rowe is an American singer and songwriter best known by her stage name SZA, acclaimed for her genre-blending R&B music and introspective lyrics.
-
E.
Mellody Hobson
Mellody Hobson is an American businesswoman and investor, best known as the co-CEO and president of Ariel Investments and a prominent advocate for financial literacy and corporate diversity.
- 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_69b3454777808190b78aa9047ba1f018 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355f2377c8190b0176b4c6776815e |
completed | March 13, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b613895488819083140ae9f0ddba5e |
completed | March 15, 2026, 2:03 a.m. |
Created at: March 12, 2026, 11:32 p.m.