Triple
T17008963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard Marks |
E412646
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Mr Nice |
E432047
|
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: Mr Nice | Statement: [Howard Marks, notableWork, Mr Nice]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mr Nice Context triple: [Howard Marks, notableWork, Mr Nice]
-
A.
Mr. Nice
chosen
Mr. Nice is a 2010 biographical crime film in which Rhys Ifans portrays real-life Welsh drug smuggler Howard Marks.
-
B.
Tim Nice-But-Dim
Tim Nice-But-Dim is a fictional, affable but spectacularly thick upper-class character from British television comedy, best known from Harry Enfield’s sketch shows.
-
C.
Greg Nice
Greg Nice is an American rapper and producer best known as one half of the hip hop duo Nice & Smooth and for his influential work in the late 1980s and 1990s New York rap scene.
-
D.
Mr. Franks
Mr. Franks is a music producer best known for his work with the hip-hop collective Legend.
-
E.
Mr. G
Mr. G is the nickname of Gustaf V, who was King of Sweden from 1907 to 1950 and one of the longest-reigning Swedish monarchs.
- 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_69e3d3853f548190910240a2145cc890 |
completed | April 18, 2026, 6:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc222d108190934ef2b3aa46aa22 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:33 a.m.