Triple
T18163119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martha Kearney |
E434817
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Woman's Hour |
—
|
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: Woman's Hour | Statement: [Martha Kearney, notableWork, Woman's Hour]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Woman's Hour Context triple: [Martha Kearney, notableWork, Woman's Hour]
-
A.
Woman's Hour
chosen
Woman's Hour is a long-running BBC Radio 4 magazine programme that focuses on issues, stories, and culture from women's perspectives.
-
B.
Loose Women
Loose Women is a long-running British daytime talk show featuring a panel of female hosts discussing current affairs, entertainment, and personal topics.
-
C.
This Morning
This Morning is a long-running British daytime television magazine show featuring a mix of news, interviews, lifestyle segments, and entertainment.
-
D.
The 6 O'Clock Show
The 6 O'Clock Show was a popular 1980s London-based television magazine programme known for its mix of light entertainment, interviews, and local interest stories.
-
E.
Good Morning Britain
Good Morning Britain is a British weekday breakfast television news and talk show featuring headlines, interviews, and topical discussions.
- 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dec419788190a999a68f32fab39b |
completed | April 19, 2026, 1:55 p.m. |
Created at: April 10, 2026, 10:30 a.m.