Triple
T12636668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makaziwe Mandela |
E301782
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Evelyn Mase |
E376883
|
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: Evelyn Mase | Statement: [Makaziwe Mandela, mother, Evelyn Mase]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evelyn Mase Context triple: [Makaziwe Mandela, mother, Evelyn Mase]
-
A.
Evelyn Mase
chosen
Evelyn Mase was a South African nurse and the first wife of Nelson Mandela, with whom she had several children including Makgatho Mandela.
-
B.
Evelyn Roff
Evelyn Roff was the wife of British poet, art critic, and anarchist philosopher Herbert Read.
-
C.
Evelyn Wade
Evelyn Wade was the wife of British mathematician and philosopher Alfred North Whitehead, known primarily in relation to his personal and intellectual life.
-
D.
Evelyn Couch
Evelyn Couch is a timid, middle-aged Southern housewife who undergoes a journey of self-discovery and empowerment in the novel and film "Fried Green Tomatoes at the Whistle Stop Cafe."
-
E.
Evelyn Gardner
Evelyn Gardner was a British socialite best known as the first wife of novelist Evelyn Waugh and a figure in interwar London’s bohemian circles.
- 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_69d7bdec9f9c8190b4bac675b7588211 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96147f49c8190b701e1e27e207a95 |
completed | April 10, 2026, 8:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f746077b288190b8ca7927352a7904 |
completed | May 3, 2026, 12:56 p.m. |
Created at: April 9, 2026, 5:16 p.m.