Triple
T11853399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Dehn |
E281965
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | James Bernard |
E456206
|
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: James Bernard | Statement: [Paul Dehn, spouse, James Bernard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Bernard Context triple: [Paul Dehn, spouse, James Bernard]
-
A.
James Bernard
chosen
James Bernard was a British composer best known for his iconic, atmospheric scores for Hammer horror films, including several Dracula movies.
-
B.
Bernard George
Bernard George was a British architect best known for designing the iconic Kensington Roof Gardens in London.
-
C.
Bernard Edward Denis
Bernard Edward Denis FitzPatrick, 2nd Baron Castletown, was an Anglo-Irish peer and landowner active in the late 19th and early 20th centuries.
-
D.
Bernard Hart
Bernard Hart was an early American financier and broker known for being among the original founders of what became the New York Stock Exchange.
-
E.
Frank Bannister
Frank Bannister is a psychic investigator and con artist who can see and communicate with ghosts in the horror-comedy film "The Frighteners."
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a696ee548190800d56c64c339b10 |
completed | April 10, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f167c9d4e88190bfaadada0450e639 |
completed | April 29, 2026, 2:07 a.m. |
Created at: April 8, 2026, 9:43 p.m.