Triple

T14516946
Position Surface form Disambiguated ID Type / Status
Subject Nothing Without You E340544 entity
Predicate writer P1360 FINISHED
Object Andre Proctor E600191 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: Andre Proctor | Statement: [Nothing Without You, writer, Andre Proctor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andre Proctor
Context triple: [Nothing Without You, writer, Andre Proctor]
  • A. Andre Proctor chosen
    Andre Proctor is a songwriter best known for co-writing the hit track "How to Love."
  • B. Andre Eric Proctor
    Andre Eric Proctor is a songwriter best known for co-writing the hit Beyoncé and Jay-Z track "Drunk in Love."
  • C. Jay Proctor
    Jay Proctor is an American soul singer best known as the lead vocalist of the 1960s group Jay & the Techniques, recognized for their hit "Apples, Peaches, Pumpkin Pie."
  • D. Mark Proctor
    Mark Proctor is an individual known primarily as a graduate of Hillsborough High School.
  • E. Jeremy Prokosch
    Jeremy Prokosch is a wealthy, domineering American film producer in Jean-Luc Godard’s 1963 film "Le Mépris," whose manipulative behavior exacerbates the marital tensions at the story’s center.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a6f50208190b687b505f5cd1aa2 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6da80dc88190afa96760efb0c7de completed May 8, 2026, 4:59 a.m.
Created at: April 10, 2026, 1:21 a.m.