Triple

T23444162
Position Surface form Disambiguated ID Type / Status
Subject Esther Rolle E565487 entity
Predicate familyName P18 FINISHED
Object Rolle
Rolle is a surname most notably associated with American actress Esther Rolle, famed for her role as Florida Evans on the television series "Good Times."
E100491 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: Rolle | Statement: [Esther Rolle, familyName, Rolle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rolle
Context triple: [Esther Rolle, familyName, Rolle]
  • A. Rolle
    Rolle is a picturesque Swiss town on the shores of Lake Geneva, known for its lakeside promenade, historic castle, and surrounding vineyards.
  • B. Roal
    Roal is a small settlement located in the Hadeland district of southeastern Norway.
  • C. Rollot
    Rollot is a small commune in northern France, notable as the birthplace of the orientalist and translator Antoine Galland.
  • D. Rolen
    Rolen is a surname most notably associated with Scott Rolen, a Hall of Fame Major League Baseball third baseman.
  • E. Romme
    Romme is a French surname most notably associated with Gilbert Romme, a prominent mathematician and revolutionary figure during the French Revolution.
  • 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: Rolle
Triple: [Esther Rolle, familyName, Rolle]
Generated description
Rolle is a surname most notably associated with American actress Esther Rolle, famed for her role as Florida Evans on the television series "Good Times."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rolle
Target entity description: Rolle is a surname most notably associated with American actress Esther Rolle, famed for her role as Florida Evans on the television series "Good Times."
  • A. Rolle chosen
    Rolle is a picturesque Swiss town on the shores of Lake Geneva, known for its lakeside promenade, historic castle, and surrounding vineyards.
  • B. Roal
    Roal is a small settlement located in the Hadeland district of southeastern Norway.
  • C. Rollot
    Rollot is a small commune in northern France, notable as the birthplace of the orientalist and translator Antoine Galland.
  • D. Rolen
    Rolen is a surname most notably associated with Scott Rolen, a Hall of Fame Major League Baseball third baseman.
  • E. Romme
    Romme is a French surname most notably associated with Gilbert Romme, a prominent mathematician and revolutionary figure during the French Revolution.
  • 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_69e24584f9488190bb32730bd2ce023e completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a64717d08190a2c25e7bbfc17a2f completed April 29, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c67b7c6b08190a739ee30e51c9f46 completed May 19, 2026, 1:37 p.m.
NEDg Description generation batch_6a0c7217edc881909f582f0c726d7e61 completed May 19, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0c76f0f4bc81909912d2196e969cf1 completed May 19, 2026, 2:42 p.m.
Created at: April 17, 2026, 5:51 p.m.