Triple
T14304068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Nelson |
E354643
|
entity |
| Predicate | workOn |
P30363
|
FINISHED |
| Object | Hard Candy |
E578363
|
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: Hard Candy | Statement: [Brian Nelson, workOn, Hard Candy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hard Candy Context triple: [Brian Nelson, workOn, Hard Candy]
-
A.
Hard Candy
Hard Candy is a pop and R&B studio album by Madonna, known for its dance-oriented sound and collaborations with producers like Timbaland and Pharrell Williams.
-
B.
Hard Candy
Hard Candy is a 2002 studio album by American rock band Counting Crows, noted for its polished pop-rock sound and melodic, radio-friendly songs.
-
C.
Hard Candy
chosen
Hard Candy is a 2005 psychological thriller film in which Elliot Page delivers a breakout performance as a teenage girl confronting a suspected sexual predator.
-
D.
Sweet Candy
Sweet Candy is a track from AC/DC's 2014 hard rock album "Rock or Bust."
-
E.
Acid Candy
Acid Candy is a vivid, hyper-stylized photographic series by British fashion photographer Miles Aldridge, known for its saturated colors and surreal, cinematic depictions of women and domestic scenes.
- 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_69d8278e17088190b328c5a9d4be74ff |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85afabe48190926d6098047f4bcf |
completed | April 14, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4682f86881908c9fb210bb9e486a |
completed | May 8, 2026, 2:12 a.m. |
Created at: April 10, 2026, 1:12 a.m.