Triple
T19896084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Offence |
E478155
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Richard Shepherd |
—
|
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: Richard Shepherd | Statement: [The Offence, producer, Richard Shepherd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Shepherd Context triple: [The Offence, producer, Richard Shepherd]
-
A.
Richard Shepherd
chosen
Richard Shepherd was an American film producer best known for his work on classic movies such as "Breakfast at Tiffany's."
-
B.
Geoffrey Faithfull
Geoffrey Faithfull was a British cinematographer known for his work on numerous films from the silent era through the mid-20th century, including the classic science fiction horror film "Village of the Damned."
-
C.
David Shire
David Shire is an American composer best known for his film and television scores, including acclaimed work in the 1970s.
-
D.
Nicholas Lea
Nicholas Lea is a Canadian actor best known for his recurring role as Alex Krycek on the television series "The X-Files."
-
E.
Peter Shepherd
Peter Shepherd is a young boy who becomes one of the central players trapped in the dangerous magical board game in the 1995 fantasy adventure film "Jumanji."
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593dba78819082c8b80e65246171 |
completed | April 20, 2026, 4:50 p.m. |
Created at: April 10, 2026, 1:52 p.m.