Triple
T21446976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Story of Temple Drake |
E529102
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Stephen Roberts |
—
|
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: Stephen Roberts | Statement: [The Story of Temple Drake, director, Stephen Roberts]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stephen Roberts Context triple: [The Story of Temple Drake, director, Stephen Roberts]
-
A.
Stephen Roberts
chosen
Stephen Roberts was an American film director active in the early 20th century, known for his work during Hollywood’s pre-Code era.
-
B.
Paul Roberts
Paul Roberts is known primarily as a former husband of acclaimed American actress Ellen Burstyn.
-
C.
Jonathan Roberts
Jonathan Roberts is an American screenwriter best known for co-writing Disney’s animated classic "The Lion King."
-
D.
Jonathan Roberts
Jonathan Roberts is a professional ballroom dancer best known for his appearances as a pro on the television show "Dancing with the Stars."
-
E.
Jonathan Roberts
Jonathan Roberts is a creator known for his work on the project or character "Scar."
- 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9cea7bc81909ee3e1cdeda1fe7e |
completed | April 23, 2026, 9:43 a.m. |
Created at: April 16, 2026, 6:06 p.m.