Triple
T3475095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarke |
E73353
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Roy Clarke |
E245547
|
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: Roy Clarke | Statement: [Clarke, hasNotableBearer, Roy Clarke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roy Clarke Context triple: [Clarke, hasNotableBearer, Roy Clarke]
-
A.
Roy Clarke
chosen
Roy Clarke is a British television comedy writer best known for creating the long-running sitcom "Last of the Summer Wine."
-
B.
Ron Clarke
Ron Clarke was an Australian long-distance runner renowned for breaking multiple world records and later becoming a prominent sports administrator and mayor.
-
C.
Johnny Speight
Johnny Speight was a British television scriptwriter best known for his sharp, socially satirical comedy and creation of controversial, working-class characters.
-
D.
Wilfred Lucas
Wilfred Lucas was a Canadian-born actor and director of the silent film era, known for his work with D. W. Griffith at Biograph Studios.
-
E.
Fred Barker
Fred Barker was an American gangster and member of the notorious Barker–Karpis gang during the early 20th-century crime wave in the United States.
- 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_69ad85b2fed48190948c8765e453d270 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb593a388190b7786190deba96ed |
completed | March 8, 2026, 6:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b36812e3a08190abe8db8d3429a49e |
completed | March 13, 2026, 1:27 a.m. |
Created at: March 8, 2026, 3:17 p.m.