Triple
T9399437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Harris |
E226429
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Layer Cake |
E285873
|
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: Layer Cake | Statement: [George Harris, notableWork, Layer Cake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Layer Cake Context triple: [George Harris, notableWork, Layer Cake]
-
A.
Layer Cake
Layer Cake is a 2004 British crime thriller film directed by Matthew Vaughn, known for its stylish depiction of London’s criminal underworld and for helping launch Daniel Craig to wider fame.
-
B.
Beecake
Beecake is a Scottish alternative rock band fronted by actor and musician Billy Boyd.
-
C.
Cake
"Cake" is a 2014 drama film in which Jennifer Aniston stars as a woman struggling with chronic pain and grief, featuring Mamie Gummer in a supporting role.
-
D.
Layer Cake (novel)
chosen
Layer Cake (novel) is a 2000 British crime thriller by J.J. Connolly that follows an unnamed London cocaine dealer navigating the dangerous criminal underworld as he plans to retire from the drug trade.
-
E.
Meringue Clouds
Meringue Clouds is a sky-themed world in New Super Mario Bros. U characterized by its airy platforms, cloud-filled landscapes, and challenging aerial levels.
- 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_69ca843170f88190800a8ab2b5fc568e |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd51556fc08190b8ff8190a1485a3a |
completed | April 1, 2026, 5:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d10121f53c8190b4fe3ce0fe04aecc |
completed | April 4, 2026, 12:16 p.m. |
Created at: March 30, 2026, 7:46 p.m.