Triple
T10466940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claire Tomalin |
E246821
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Rebecca Frayn |
E865694
|
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: Rebecca Frayn | Statement: [Claire Tomalin, hasChild, Rebecca Frayn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rebecca Frayn Context triple: [Claire Tomalin, hasChild, Rebecca Frayn]
-
A.
Michael Frayn
Michael Frayn is an English playwright, novelist, and translator best known for his farce "Noises Off" and the philosophical drama "Copenhagen."
-
B.
Miriam Stoppard
Miriam Stoppard is a British physician, television presenter, and prolific author best known for her popular health and parenting advice books.
-
C.
Frankie Frayn
chosen
Frankie Frayn is a child of the acclaimed British biographer and literary journalist Claire Tomalin.
-
D.
Caryl Churchill
Caryl Churchill is a renowned British playwright known for her innovative, politically charged, and formally experimental works for the stage.
-
E.
Siri Pinter
Siri Pinter is an American food blogger and television producer best known as the wife of TV host Carson Daly.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5092e3230819098ab444f73c9bd40 |
completed | April 7, 2026, 1:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94b047b588190a116f4fbd4cdbc35 |
completed | April 10, 2026, 7:09 p.m. |
Created at: April 6, 2026, 12:19 p.m.