Triple
T14942678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Kelly |
E372568
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Bill |
E460358
|
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: The Bill | Statement: [Craig Kelly, notableWork, The Bill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Bill Context triple: [Craig Kelly, notableWork, The Bill]
-
A.
The Bill
chosen
The Bill is a long-running British police procedural television series that focuses on the lives and work of officers at the fictional Sun Hill police station in London.
-
B.
Don't Mess with Bill
"Don't Mess with Bill" is a 1965 Motown soul single by The Marvelettes, written by Smokey Robinson and known for its smooth groove and assertive romantic lyrics.
-
C.
Bill (2015 film)
Bill (2015 film) is a British family comedy that offers a humorous, fictionalized account of William Shakespeare’s early life, created by members of the Horrible Histories troupe.
-
D.
News at Ten
News at Ten is the BBC’s flagship late-evening television news bulletin, providing in-depth national and international news coverage each night.
-
E.
Brassic
Brassic is a British comedy-drama television series that follows a group of working-class friends in a small Northern town as they navigate crime, chaos, and everyday life.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68c1df0819084c0cd61b207d398 |
completed | April 15, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e9484e8819086ca6a59d672e49d |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:38 a.m.