Triple

T20673913
Position Surface form Disambiguated ID Type / Status
Subject Dee Dee Sharp E508109 entity
Predicate stageName P7872 FINISHED
Object Dee Dee Sharp NE NERFINISHED

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: Dee Dee Sharp | Statement: [Dee Dee Sharp, stageName, Dee Dee Sharp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dee Dee Sharp
Context triple: [Dee Dee Sharp, stageName, Dee Dee Sharp]
  • A. Dee Dee Sharp chosen
    Dee Dee Sharp is an American R&B singer best known for her early-1960s dance hits and contributions to the Philadelphia soul sound.
  • B. Dee Dee Warwick
    Dee Dee Warwick was an American soul and R&B singer known for hits in the 1960s and 1970s and for being part of the musical Warwick–Houston family.
  • C. Frankie Miller
    Frankie Miller is a Scottish rock and blues singer-songwriter known for his powerful, soulful voice and hits such as "Darlin'" and "Be Good to Yourself."
  • D. Dee Dee
    Dee Dee is Dexter’s exuberant and mischievous older sister in the animated series "Dexter’s Laboratory," known for constantly disrupting his scientific experiments.
  • E. Dee Dee
    Dee Dee Blanchard was an American woman whose murder in 2015 exposed her long-term abuse of her daughter Gypsy Rose through Munchausen syndrome by proxy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5cca8808190a60ee28c7ea46412 completed April 20, 2026, 11:25 p.m.
Created at: April 16, 2026, 11:44 a.m.