Triple
T21126492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dolly Pentreath |
E520570
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Dolly Pentreath |
—
|
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: Dolly Pentreath | Statement: [Dolly Pentreath, name, Dolly Pentreath]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dolly Pentreath Context triple: [Dolly Pentreath, name, Dolly Pentreath]
-
A.
Dolly Pentreath
chosen
Dolly Pentreath was an 18th-century woman from Mousehole in Cornwall often regarded as the last fluent traditional native speaker of the Cornish language.
-
B.
Dolly Sharp
Dolly Sharp was an American adult film actress best known for her role in the landmark 1972 pornographic film "Deep Throat."
-
C.
Polly Wright
Polly Wright is a companion of the Second Doctor in the long-running British science fiction television series Doctor Who.
-
D.
Sophie Wright
Sophie Wright is a British chef and food writer known for her cookbooks, television appearances, and work promoting accessible, seasonal cooking.
-
E.
Ruth Madoc
Ruth Madoc was a Welsh actress best known for her comedic role as Gladys Pugh in the BBC sitcom "Hi-de-Hi!" and for her extensive work in British television and theatre.
- 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_69e0b50a623881909c0bbaf4f2c055e7 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e72239965c819081b4077b914d0a98 |
completed | April 21, 2026, 7:07 a.m. |
Created at: April 16, 2026, 2:56 p.m.