Triple
T16841637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emma Barnett |
E409426
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Emma Barnett |
E409426
|
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: Emma Barnett | Statement: [Emma Barnett, name, Emma Barnett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emma Barnett Context triple: [Emma Barnett, name, Emma Barnett]
-
A.
Emma Barnett
chosen
Emma Barnett is a British journalist and broadcaster best known as a prominent BBC presenter and interviewer.
-
B.
Elizabeth Berrington
Elizabeth Berrington is a British actress known for her work in television, film, and theatre, including prominent roles in series such as The Syndicate.
-
C.
Florence Balcombe
Florence Balcombe was an Irish socialite best known as the wife of Dracula author Bram Stoker and formerly a romantic interest of Oscar Wilde.
-
D.
Dorothy Buxton
Dorothy Buxton was a British social reformer and humanitarian best known for co-founding the international child welfare organization Save the Children.
-
E.
Enid Bennett
Enid Bennett was an Australian-born silent film actress who became a popular leading lady in early Hollywood cinema.
- 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_69d883952b048190887740a980b712ed |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b35167a48190b45a459023e3ab1b |
completed | April 18, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012327b68881908ad5f4e2fe03f56a |
completed | May 11, 2026, 12:30 a.m. |
Created at: April 10, 2026, 5:24 a.m.