Triple
T15905222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aaron Yoo |
E385694
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Disturbia |
E362609
|
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: Disturbia | Statement: [Aaron Yoo, notableWork, Disturbia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Disturbia Context triple: [Aaron Yoo, notableWork, Disturbia]
-
A.
Disturbia
chosen
Disturbia is a 2007 thriller film about a troubled teenager under house arrest who becomes convinced his neighbor is a serial killer.
-
B.
Bad Romance
"Bad Romance" is a hit pop song by Lady Gaga, known for its dark, theatrical style and iconic music video.
-
C.
Run This Town
Run This Town is a 2019 political drama film that follows young journalists investigating a scandal involving Toronto mayor Rob Ford.
-
D.
Run This Town
"Run This Town" is a 2009 hip-hop single by Jay-Z featuring Rihanna and Kanye West, known for its anthemic chorus and dark, triumphant production.
-
E.
Alright, Still
"Alright, Still" is the 2006 debut studio album by English singer-songwriter Lily Allen, blending pop, ska, and reggae influences with witty, observational lyrics.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565956588190ba4726a2879b677d |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb0535a808190983b4ff028826cbf |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:52 a.m.