Triple
T11423281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Niger–Congo |
E270680
|
entity |
| Predicate | researchedBy |
P1945
|
FINISHED |
| Object | Kay Williamson |
E586689
|
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: Kay Williamson | Statement: [Proto-Niger–Congo, researchedBy, Kay Williamson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kay Williamson Context triple: [Proto-Niger–Congo, researchedBy, Kay Williamson]
-
A.
Kay Williamson
chosen
Kay Williamson was a prominent British linguist and Africanist renowned for her pioneering research on Nigerian and Bantu languages, particularly within the Niger-Congo family.
-
B.
Elizabeth Arlen
Elizabeth Arlen is an actress best known for her role in the 1990 supernatural horror-thriller film "The First Power."
-
C.
Kay Young
Kay Young was a British actress known for her stage and film work in the mid-20th century.
-
D.
Jay Griffiths
Jay Griffiths is a British writer and essayist known for her explorations of nature, culture, and freedom in works such as "Wild" and "Pip Pip."
-
E.
Kate Harwood
Kate Harwood is a British television producer and executive known for her work on high-profile drama series, including the acclaimed crime drama "Luther."
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d801b357e88190ace56d36a945688f |
completed | April 9, 2026, 7:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b8a1e88c8190994bea88a0490e60 |
completed | April 20, 2026, 5:24 a.m. |
Created at: April 8, 2026, 9:35 p.m.