Triple

T10750090
Position Surface form Disambiguated ID Type / Status
Subject Upside Down E253549 entity
Predicate hasBside P15273 FINISHED
Object Friend to Friend E883963 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: Friend to Friend | Statement: [Upside Down, hasBside, Friend to Friend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Friend to Friend
Context triple: [Upside Down, hasBside, Friend to Friend]
  • A. Friend to Friend chosen
    "Friend to Friend" is a song by Diana Ross from her 1980 self-titled album.
  • B. Circle of Friends
    Circle of Friends is a 1995 romantic drama film, based on Maeve Binchy’s novel, in which Alan Cumming appears alongside Minnie Driver and Chris O’Donnell.
  • C. Friends Will Be Friends
    "Friends Will Be Friends" is a 1986 rock song by the British band Queen, known for its anthemic chorus celebrating loyalty and camaraderie.
  • D. Friend of Mine
    "Friend of Mine" is a track by The Notorious B.I.G. from his landmark 1994 debut hip-hop album *Ready to Die*.
  • E. Thank You for Being a Friend
    "Thank You for Being a Friend" is a pop song written and originally recorded by Andrew Gold, best known as the theme song for the television sitcom *The Golden Girls*.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71dbfe5f481908eed42328447b158 completed April 9, 2026, 3:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69de55a12b8c8190bbeeb6d176f42b49 completed April 14, 2026, 2:56 p.m.
Created at: April 8, 2026, 9:15 p.m.