Triple
T21994081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Girls on Top |
E543158
|
entity |
| Predicate | notableWorkOf |
P4
|
FINISHED |
| Object | Ruby Wax |
—
|
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: Ruby Wax | Statement: [Girls on Top, notableWorkOf, Ruby Wax]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ruby Wax Context triple: [Girls on Top, notableWorkOf, Ruby Wax]
-
A.
Ruby Wax
chosen
Ruby Wax is an American-British comedian, actress, and mental health campaigner known for her sharp, satirical interviewing style on British television.
-
B.
Helen Zaltzman
Helen Zaltzman is a British podcaster and broadcaster best known for creating and hosting the linguistics show "The Allusionist" and co-founding the comedy podcast "Answer Me This!".
-
C.
Jenni Murray
Jenni Murray is a British journalist and broadcaster best known for her long tenure as the presenter of BBC Radio 4’s Woman’s Hour.
-
D.
Sarah Wainthrope
Sarah Wainthrope is an individual known primarily through her association as a friend of John Tate.
-
E.
Alan Carr
Alan Carr is a British comedian and television presenter known for his stand-up comedy, chat shows like "Alan Carr: Chatty Man," and numerous hosting roles on UK television.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127639bf48190800b3fa3c1527983 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:17 p.m.