Triple

T12991114
Position Surface form Disambiguated ID Type / Status
Subject Empress E321906 entity
Predicate hasTrack P3284 FINISHED
Object Control
"Control" is a song by the American R&B singer Empress.
E1013991 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: Control | Statement: [Empress, hasTrack, Control]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Control
Context triple: [Empress, hasTrack, Control]
  • A. Control
    Control is Janet Jackson's breakthrough 1986 studio album that established her as a major pop and R&B star through its assertive themes and innovative production.
  • B. Control
    "Control" is the second studio album by American pop group Dream Street, showcasing their teen pop sound in the early 2000s.
  • C. Control
    Control is a 2007 black-and-white biographical film directed by Anton Corbijn that portrays the life and tragic death of Joy Division frontman Ian Curtis.
  • D. Control
    Control is a critically acclaimed third-person action-adventure video game known for its surreal narrative, paranormal abilities, and striking brutalist setting.
  • E. Control
    Control is a competitive objective-based multiplayer game mode in Call of Duty where teams alternate between attacking and defending limited capture points with a shared pool of lives.
  • 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: Control
Triple: [Empress, hasTrack, Control]
Generated description
"Control" is a song by the American R&B singer Empress.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Control
Target entity description: "Control" is a song by the American R&B singer Empress.
  • A. Control
    "Control" is a prominent hip-hop track by Big Sean featuring Kendrick Lamar and Jay Electronica, widely known for Kendrick Lamar's provocative verse calling out fellow rappers.
  • B. Control
    "Control" is the second studio album by American pop group Dream Street, showcasing their teen pop sound in the early 2000s.
  • C. Control
    Control is Janet Jackson's breakthrough 1986 studio album that established her as a major pop and R&B star through its assertive themes and innovative production.
  • D. Control
    Control is a critically acclaimed third-person action-adventure video game known for its surreal narrative, paranormal abilities, and striking brutalist setting.
  • E. Control
    Control is a 2007 black-and-white biographical film directed by Anton Corbijn that portrays the life and tragic death of Joy Division frontman Ian Curtis.
  • 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_69d8076479b8819090afce3591939cdf completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e7765788190a9503ef055bc30ca completed April 10, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8fb70f481908a9a4ca04d6bf93b completed May 3, 2026, 2:54 a.m.
NEDg Description generation batch_69f6baa76e8c8190b84fd31657ef3385 completed May 3, 2026, 3:01 a.m.
NED2 Entity disambiguation (via description) batch_69f6bb7a0ae08190813411fa677430aa completed May 3, 2026, 3:05 a.m.
Created at: April 9, 2026, 8:43 p.m.