Triple
T18875612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Revenge of Frankenstein |
E461675
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Anthony Hinds |
—
|
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: Anthony Hinds | Statement: [The Revenge of Frankenstein, producer, Anthony Hinds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anthony Hinds Context triple: [The Revenge of Frankenstein, producer, Anthony Hinds]
-
A.
Anthony Hinds
chosen
Anthony Hinds was a prominent British film producer and screenwriter best known for his influential work on Hammer Films’ classic horror movies in the mid-20th century.
-
B.
R.J. Lewis
R.J. Lewis is a fictional character from the soap opera "Guiding Light," known as the son of Josh Lewis.
-
C.
Timothy Fall
Timothy Fall is an actor known for his role in the British television sitcom "Bob."
-
D.
Matthew C. Wheeler
Matthew C. Wheeler is an atmospheric scientist best known for developing the widely used Real-time Multivariate MJO (RMM) index for monitoring the Madden–Julian Oscillation.
-
E.
Anthony Hayes
Anthony Hayes is an Australian actor and filmmaker known for his work in film and television, as well as for co-founding the production company Blue-Tongue Films.
- 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c3ce07788190a179705eb1b6c824 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 10, 2026, 11:57 a.m.