Triple
T12698974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De-Lovely |
E303406
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Jay Cocks |
E326263
|
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: Jay Cocks | Statement: [De-Lovely, screenwriter, Jay Cocks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jay Cocks Context triple: [De-Lovely, screenwriter, Jay Cocks]
-
A.
Jay Cocks
chosen
Jay Cocks is an American screenwriter and film critic best known for his collaborations with director Martin Scorsese on historical and character-driven dramas.
-
B.
Mick Cocks
Mick Cocks was an Australian rock guitarist best known for his work with the hard rock band Rose Tattoo and his influential role in the country’s pub rock scene.
-
C.
Michael Graham Cox
Michael Graham Cox was a British actor best known for his voice and character roles in film, television, and radio, including work on animated adaptations of classic literature.
-
D.
Danny Cox
Danny Cox is a former Major League Baseball right-handed pitcher best known for his years with the St. Louis Cardinals during the 1980s.
-
E.
Peter Cookson
Peter Cookson was an American stage and screen actor active in the mid-20th century, known for his work on Broadway and in films.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961ed26588190ae76ff17159e06ec |
completed | April 10, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684e2292c8190bffb3a8b6e15029c |
completed | May 2, 2026, 11:12 p.m. |
Created at: April 9, 2026, 5:22 p.m.