Triple
T18975584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Brides of Dracula |
E464285
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Alfred Cox |
—
|
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: Alfred Cox | Statement: [The Brides of Dracula, editor, Alfred Cox]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alfred Cox Context triple: [The Brides of Dracula, editor, Alfred Cox]
-
A.
Alfred Cox
Alfred Cox was an architect known for designing Kingston Museum in Kingston upon Thames, England.
-
B.
Alfred Cox
chosen
Alfred Cox is an editor known for his work on the British horror film "The Revenge of Frankenstein."
-
C.
George Aldrich
George Aldrich is a NASA contamination control specialist known for his long career testing materials for off-gassing to ensure astronaut safety on space missions.
-
D.
Arthur Hiller
Arthur Hiller was a Canadian-born film director best known for popular Hollywood movies such as "Love Story" and "The In-Laws."
-
E.
Brian O’Hara
Brian O’Hara was an English musician best known as the guitarist and vocalist for the Liverpool Merseybeat band The Fourmost during the 1960s.
- 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61e71988190817cada25672a1ce |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon