Triple

T13995792
Position Surface form Disambiguated ID Type / Status
Subject Chasing Lights E336692 entity
Predicate notableTrack P8087 FINISHED
Object Keep Her
"Keep Her" is a song by British-Irish girl group The Saturdays from their debut album "Chasing Lights."
 E1074187 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: Keep Her | Statement: [Chasing Lights, notableTrack, Keep Her]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keep Her
Context triple: [Chasing Lights, notableTrack, Keep Her]
  • A. Pieces of Her
    Pieces of Her is a thriller drama television series, based on Karin Slaughter’s novel, that follows a woman who discovers shocking secrets about her seemingly ordinary mother after a violent incident.
  • B. Let Her
    "Let Her" is a song featured on Esperanza Spalding’s jazz-influenced album *Radio Music Society*.
  • C. Cheaper to Keep Her
    "Cheaper to Keep Her" is a soul and R&B song, originally popularized by Johnnie Taylor, known for its humorous take on the financial pitfalls of divorce.
  • D. Her Too
    "Her Too" is a soulful R&B song by American singer-songwriter SiR, known for its smooth production and introspective lyrics.
  • E. Til Death
    Til Death is an American sitcom that follows the comedic ups and downs of a long-married couple, starring Brad Garrett and Joely Fisher.
  • 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: Keep Her
Triple: [Chasing Lights, notableTrack, Keep Her]
Generated description
"Keep Her" is a song by British-Irish girl group The Saturdays from their debut album "Chasing Lights."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keep Her
Target entity description: "Keep Her" is a song by British-Irish girl group The Saturdays from their debut album "Chasing Lights."
  • A. Pieces of Her
    Pieces of Her is a thriller drama television series, based on Karin Slaughter’s novel, that follows a woman who discovers shocking secrets about her seemingly ordinary mother after a violent incident.
  • B. Let Her
    "Let Her" is a song featured on Esperanza Spalding’s jazz-influenced album *Radio Music Society*.
  • C. Cheaper to Keep Her
    "Cheaper to Keep Her" is a soul and R&B song, originally popularized by Johnnie Taylor, known for its humorous take on the financial pitfalls of divorce.
  • D. Her Too
    "Her Too" is a soulful R&B song by American singer-songwriter SiR, known for its smooth production and introspective lyrics.
  • E. Til Death
    Til Death is an American sitcom that follows the comedic ups and downs of a long-married couple, starring Brad Garrett and Joely Fisher.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb53f508190855cd69b8061dd77 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9d4a54819091c7efbeb4dcc5f7 completed May 6, 2026, 9:03 p.m.
NEDg Description generation batch_69fbadc6cb2c8190bdf66ad1fa6dd392 completed May 6, 2026, 9:08 p.m.
NED2 Entity disambiguation (via description) batch_69fbb01071408190a85e5e9be0150593 completed May 6, 2026, 9:18 p.m.
Created at: April 9, 2026, 10:19 p.m.