Triple
T20472674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waking the Dead |
E502230
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Robert Dillon |
—
|
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: Robert Dillon | Statement: [Waking the Dead, screenwriter, Robert Dillon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Dillon Context triple: [Waking the Dead, screenwriter, Robert Dillon]
-
A.
Robert Dillon
chosen
Robert Dillon is an American screenwriter known for his work on genre films, including the 1963 science-fiction horror movie "The Man with the X-Ray Eyes."
-
B.
James Doran
James Doran was a screenwriter best known for adapting Len Deighton’s spy novel "The Ipcress File" for the 1965 film.
-
C.
Sam Daly
Sam Daly is an American actor known for roles in film and television and as the son of actor Tim Daly.
-
D.
Tom Henighan
Tom Henighan is a researcher and co-author known for his work in large-scale language models and AI, including contributions to influential OpenAI publications.
-
E.
John Quinlan
John Quinlan was a Roman Catholic bishop who served as the third Bishop of Mobile, Alabama, in the 19th century.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69962d810819091bb13fe73250e24 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.