Triple

T9869766
Position Surface form Disambiguated ID Type / Status
Subject Sherry Darling E239925 entity
Predicate hasTitleCharacter P5716 FINISHED
Object Sherry E646910 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: Sherry | Statement: [Sherry Darling, hasTitleCharacter, Sherry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sherry
Context triple: [Sherry Darling, hasTitleCharacter, Sherry]
  • A. Sherry chosen
    Sherry is a feminine given name commonly used in English-speaking countries, often associated with names like Cheryl or derived from the fortified wine sherry.
  • B. Sherry
    Sherry is a surname most notably associated with William Grant Sherry, an American painter and the third husband of actress Bette Davis.
  • C. Manzanilla sherry
    Manzanilla sherry is a pale, dry style of fino sherry uniquely aged under flor yeast by the sea in Sanlúcar de Barrameda, giving it a distinctive light, salty character.
  • D. Vino
    Vino is a VNC-compatible remote desktop server for the GNOME desktop environment on Unix-like systems.
  • E. Pedro Ximénez sweet sherry
    Pedro Ximénez sweet sherry is a rich, dark, intensely sweet Spanish dessert wine made from sun-dried Pedro Ximénez grapes, known for its raisin, fig, and caramel flavors.
  • 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_69ca84e7506c819095cbde4ff16512bb completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb3d498b481908f82f31f98b57c7e completed April 2, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e46209988190b97aefee6cbddbad completed April 5, 2026, 4:26 a.m.
Created at: March 30, 2026, 8:36 p.m.