Triple

T19129627
Position Surface form Disambiguated ID Type / Status
Subject Heaux Tales E468280 entity
Predicate hasPart P35 FINISHED
Object On It
"On It" is a sensual R&B song by Jazmine Sullivan featuring Ari Lennox from the acclaimed project *Heaux Tales*.
 E1360184 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: On It | Statement: [Heaux Tales, hasPart, On It]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: On It
Context triple: [Heaux Tales, hasPart, On It]
  • A. Get It On
    "Get It On" is a 1971 glam rock song by T. Rex that became one of the band's biggest hits and a defining track of the glam rock era.
  • B. Who Is It
    "Who Is It" is a 1992 song by Michael Jackson, known for its dark, paranoid themes and intricate vocal arrangements.
  • C. Who Is It
    "Who Is It" is an a cappella-driven experimental pop song by Icelandic artist Björk from her 2004 album Medúlla.
  • D. All of It
    All of It is a theatrical work best known as a prominent stage performance by British actress Kate O’Flynn.
  • E. Did It B4
    "Did It B4" is a track by Chicago rapper Chance the Rapper from his acclaimed 2013 mixtape INNANETAPE.
  • 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: On It
Triple: [Heaux Tales, hasPart, On It]
Generated description
"On It" is a sensual R&B song by Jazmine Sullivan featuring Ari Lennox from the acclaimed project *Heaux Tales*.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: On It
Target entity description: "On It" is a sensual R&B song by Jazmine Sullivan featuring Ari Lennox from the acclaimed project *Heaux Tales*.
  • A. Get It On
    "Get It On" is a 1971 glam rock song by T. Rex that became one of the band's biggest hits and a defining track of the glam rock era.
  • B. Who Is It
    "Who Is It" is a 1992 song by Michael Jackson, known for its dark, paranoid themes and intricate vocal arrangements.
  • C. Who Is It
    "Who Is It" is an a cappella-driven experimental pop song by Icelandic artist Björk from her 2004 album Medúlla.
  • D. All of It
    All of It is a theatrical work best known as a prominent stage performance by British actress Kate O’Flynn.
  • E. Did It B4
    "Did It B4" is a track by Chicago rapper Chance the Rapper from his acclaimed 2013 mixtape INNANETAPE.
  • 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3cf8d348190b27fc7d7d39f46f1 completed April 20, 2026, 8:29 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05e67d781c8190816cb9db0ea68225 completed May 14, 2026, 3:13 p.m.
NEDg Description generation batch_6a05e7aa810081908d33193d8dcc88a9 completed May 14, 2026, 3:18 p.m.
NED2 Entity disambiguation (via description) batch_6a05ebe95e248190aecaa3625d14a2ea completed May 14, 2026, 3:36 p.m.
Created at: April 10, 2026, 12:05 p.m.