Triple
T2651537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Layer Cake |
E53909
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
J. J. Connolly
J. J. Connolly is a British author and screenwriter best known for his crime novel "Layer Cake" and its film adaptation.
|
E285872
|
NE FINISHED |
How this triple was built (4 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: J. J. Connolly | Statement: [Layer Cake, screenwriter, J. J. Connolly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: J. J. Connolly Context triple: [Layer Cake, screenwriter, J. J. Connolly]
-
A.
Mark O’Connor
Mark O’Connor is an American violinist, composer, and fiddler renowned for blending classical, jazz, and American folk traditions, particularly in contemporary string music.
-
B.
Christian O'Connell
Christian O'Connell is a British radio DJ, comedian, and author best known for hosting popular breakfast shows in the UK and Australia.
-
C.
Marc Connelly
Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
-
D.
Andrew McElfresh
Andrew McElfresh is an American comedy writer and screenwriter known for his work on films such as "White Chicks."
-
E.
Martin Connor
Martin Connor is a film editor known for his work on the biographical war drama "The Railway Man."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: J. J. Connolly Triple: [Layer Cake, screenwriter, J. J. Connolly]
Generated description
J. J. Connolly is a British author and screenwriter best known for his crime novel "Layer Cake" and its film adaptation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: J. J. Connolly Target entity description: J. J. Connolly is a British author and screenwriter best known for his crime novel "Layer Cake" and its film adaptation.
-
A.
Mark O’Connor
Mark O’Connor is an American violinist, composer, and fiddler renowned for blending classical, jazz, and American folk traditions, particularly in contemporary string music.
-
B.
Christian O'Connell
Christian O'Connell is a British radio DJ, comedian, and author best known for hosting popular breakfast shows in the UK and Australia.
-
C.
Marc Connelly
Marc Connelly was an American playwright, director, and member of the Algonquin Round Table who won the Pulitzer Prize for Drama for "The Green Pastures."
-
D.
Andrew McElfresh
Andrew McElfresh is an American comedy writer and screenwriter known for his work on films such as "White Chicks."
-
E.
Martin Connor
Martin Connor is a film editor known for his work on the biographical war drama "The Railway Man."
- F. None of above. chosen
Provenance (5 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_69ab495e192081909c77b622e8e7e15a |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abd93071248190820197936e3167f7 |
completed | March 7, 2026, 7:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af98ce81fc8190b7c6c66acfcb87c7 |
completed | March 10, 2026, 4:06 a.m. |
| NEDg | Description generation | batch_69af99416924819099d4acb1a2d60e0c |
completed | March 10, 2026, 4:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69af99adadb08190a44f2286b25bf0aa |
completed | March 10, 2026, 4:10 a.m. |
Created at: March 6, 2026, 9:53 p.m.