Triple
T18622713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phyllis Nicolson |
E455195
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | John Crank |
—
|
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: John Crank | Statement: [Phyllis Nicolson, collaboratedWith, John Crank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Crank Context triple: [Phyllis Nicolson, collaboratedWith, John Crank]
-
A.
John Crank
chosen
John Crank was a British mathematician and physicist best known for co-developing the Crank–Nicolson numerical method for solving partial differential equations.
-
B.
George Forsythe
George Forsythe was an American mathematician and computer scientist regarded as a pioneer of numerical analysis and a key figure in establishing computer science as an academic discipline.
-
C.
R. K. Kirkwood
R. K. Kirkwood is a physicist known for his contributions to plasma physics and high-energy-density science.
-
D.
Robert Leighton
Robert Leighton is a film editor known for his work on notable movies including the baseball romantic comedy "Bull Durham."
-
E.
John Randall
John Randall is a member of the Randall family, known primarily in relation to Rebecca Randall.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f020fa08190bd78d72182496b19 |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.