Triple
T17029009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intolerable Cruelty |
E413140
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Robert Ramsey |
E466640
|
NE FINISHED |
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 Ramsey | Statement: [Intolerable Cruelty, screenwriter, Robert Ramsey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Ramsey Context triple: [Intolerable Cruelty, screenwriter, Robert Ramsey]
-
A.
Robert Ramsey
chosen
Robert Ramsey is an American screenwriter known for co-writing the comedy film "Soul Men" and other Hollywood screenplays.
-
B.
Donald Ramsey
Donald Ramsey is a musician best known for his performance work on the album "Breathless."
-
C.
Neil Buchanan
Neil Buchanan is a British television presenter, artist, and musician best known for hosting the children's art show "Art Attack."
-
D.
Brian McAuliffe
Brian McAuliffe is a personal name that may refer to multiple individuals, including professionals in fields such as business, law, or public service.
-
E.
Rob Rickards
Rob Rickards is a central fictional news professional featured in the Australian television drama series "The Newsreader."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d858448190acfe81f10d83ed4b |
completed | April 18, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b553c588190b46785b85142dce5 |
completed | May 10, 2026, 11:57 p.m. |
Created at: April 10, 2026, 5:33 a.m.