Triple

T22777600
Position Surface form Disambiguated ID Type / Status
Subject Shirley MacLean Beaty E563745 entity
Predicate notableWork P4 FINISHED
Object Coco (stage musical) 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: Coco (stage musical) | Statement: [Shirley MacLean Beaty, notableWork, Coco (stage musical)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coco (stage musical)
Context triple: [Shirley MacLean Beaty, notableWork, Coco (stage musical)]
  • A. Coco (Broadway musical) chosen
    Coco is a 1969 Broadway musical about the life of fashion designer Coco Chanel, featuring a score by André Previn and a book by Alan Jay Lerner.
  • B. COCO
    COCO is a large-scale, richly annotated image dataset widely used in computer vision research for tasks like object detection, segmentation, and captioning.
  • C. Coco
    Coco is the debut studio album by American singer-songwriter Colbie Caillat, featuring her breakout hit "Bubbly" and a laid-back acoustic pop sound.
  • D. Coco
    "Coco" is a notable work by Jason Katz, recognized for its creative storytelling and distinctive artistic style.
  • E. Coco
    Coco is a character in the satirical horror-thriller film "Velvet Buzzsaw," which explores the dark side of the contemporary art world.
  • 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_69e24554497c819080b996e071de27c2 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17b6260a8819080e57481281dfe40 completed April 29, 2026, 3:30 a.m.
Created at: April 17, 2026, 3:28 p.m.