Triple
T21229847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Keep |
E523177
|
entity |
| Predicate | specialEffectsSupervisor |
P3489
|
FINISHED |
| Object | Nick Allder |
—
|
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: Nick Allder | Statement: [The Keep, specialEffectsSupervisor, Nick Allder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nick Allder Context triple: [The Keep, specialEffectsSupervisor, Nick Allder]
-
A.
Nick Allder
chosen
Nick Allder is a British special effects supervisor and visual effects artist known for his work on films such as "Alien" and "The Fifth Element."
-
B.
Nick Roud
Nick Roud is an actor known for his role in the film "Finding Neverland."
-
C.
Nick Ramm
Nick Ramm is a musician and keyboardist best known for his work with the British nu-jazz and electronic group The Cinematic Orchestra.
-
D.
Nick Caistor
Nick Caistor is a British translator and writer renowned for bringing major works of Spanish and Latin American literature, including novels by Isabel Allende, into English.
-
E.
Mark Alder
Mark Alder is a fictional character in Ken Follett's World War II-era thriller novel "Night Over Water."
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734ae60408190a9480b27d109b8fc |
completed | April 21, 2026, 8:26 a.m. |
Created at: April 16, 2026, 3:45 p.m.