Triple

T16937866
Position Surface form Disambiguated ID Type / Status
Subject Ella Henderson E410875 entity
Predicate notableWork P4 FINISHED
Object Hold On Me
"Hold On Me" is a pop song by British singer-songwriter Ella Henderson, showcasing her powerful vocals and emotive, contemporary style.
 E835474 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: Hold On Me | Statement: [Ella Henderson, notableWork, Hold On Me]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hold On Me
Context triple: [Ella Henderson, notableWork, Hold On Me]
  • A. Hold On Me
    "Hold On Me" is a song featured on Esperanza Spalding’s jazz-influenced album *Radio Music Society*.
  • B. Hold for Me
    Hold for Me is a Google Phone feature that uses AI to wait on hold during calls and alerts you when a human representative returns.
  • C. Hold Me
    "Hold Me" is a song featured on Kenny Rogers' 1983 country-pop album "Eyes That See in the Dark," which was largely written and produced by the Bee Gees.
  • D. Hold Me
    "Hold Me" is a 1985 pop album by American singer Laura Branigan that showcases her powerful vocals in a mix of synth-driven and adult contemporary tracks.
  • E. Hold Me
    "Hold Me" is an episode of the animated television series Rocket Power, centered on the adventures of a group of extreme-sports-loving kids.
  • 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: Hold On Me
Triple: [Ella Henderson, notableWork, Hold On Me]
Generated description
"Hold On Me" is a pop song by British singer-songwriter Ella Henderson, showcasing her powerful vocals and emotive, contemporary style.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hold On Me
Target entity description: "Hold On Me" is a pop song by British singer-songwriter Ella Henderson, showcasing her powerful vocals and emotive, contemporary style.
  • A. Hold On Me chosen
    "Hold On Me" is a song featured on Esperanza Spalding’s jazz-influenced album *Radio Music Society*.
  • B. Hold for Me
    Hold for Me is a Google Phone feature that uses AI to wait on hold during calls and alerts you when a human representative returns.
  • C. Hold Me
    "Hold Me" is a song featured on Kenny Rogers' 1983 country-pop album "Eyes That See in the Dark," which was largely written and produced by the Bee Gees.
  • D. Hold Me
    "Hold Me" is a 1985 pop album by American singer Laura Branigan that showcases her powerful vocals in a mix of synth-driven and adult contemporary tracks.
  • E. Hold Me
    "Hold Me" is an episode of the animated television series Rocket Power, centered on the adventures of a group of extreme-sports-loving kids.
  • F. None of above.

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_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cf2b88bc8190aeb7b07032478ae3 completed April 18, 2026, 6:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfe5210c8190873be6ccf2369b34 completed May 10, 2026, 6:35 p.m.
NEDg Description generation batch_6a00d0a1ae0c81909b09504908d56a98 completed May 10, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_6a00d1366f4c8190b5627f67402d96a0 completed May 10, 2026, 6:40 p.m.
Created at: April 10, 2026, 5:30 a.m.