Triple
T20204298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mervyn Johns |
E493308
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mervyn Johns |
—
|
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: Mervyn Johns | Statement: [Mervyn Johns, name, Mervyn Johns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mervyn Johns Context triple: [Mervyn Johns, name, Mervyn Johns]
-
A.
Mervyn Johns
chosen
Mervyn Johns was a Welsh character actor best known for his prolific work in British films of the 1940s, including the classic horror anthology "Dead of Night."
-
B.
Mervyn Spence
Mervyn Spence is a Northern Irish rock bassist and vocalist known for his work with bands such as Wishbone Ash and Trapeze.
-
C.
Mervyn Warren
Mervyn Warren is an American composer, record producer, and arranger best known for his work in film scores, gospel, and a cappella music, including as a founding member of Take 6.
-
D.
Maurice Denham
Maurice Denham was an English character actor known for his extensive work in film, television, and radio from the mid-20th century onward.
-
E.
Mervyn Weich
Mervyn Weich is an American businessman best known as the founder of the membership-based warehouse retail chain BJ's Wholesale Club.
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d8f90108190b72e37c0056de0f8 |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:38 p.m.