Triple

T4277679
Position Surface form Disambiguated ID Type / Status
Subject PostScript E97080 entity
Predicate supports P516 FINISHED
Object Bezier curves E155915 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: Bezier curves | Statement: [PostScript, supports, Bezier curves]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bezier curves
Context triple: [PostScript, supports, Bezier curves]
  • A. Bezier curves chosen
    Bézier curves are mathematically defined parametric curves widely used in computer graphics and digital design to model smooth, scalable shapes and paths.
  • B. Catmull–Rom spline
    The Catmull–Rom spline is a type of interpolating spline commonly used in computer graphics and animation to create smooth curves that pass through a given set of control points.
  • C. B-splines
    B-splines are piecewise polynomial functions widely used in computer graphics and numerical analysis to create smooth, flexible curves and surfaces controlled by a set of control points.
  • D. Page curve
    The Page curve is a theoretical prediction in black hole physics that describes how the entanglement entropy of Hawking radiation should rise and then fall over time if black hole evaporation is ultimately unitary.
  • E. Curve division
    Curve division is the plus-size and curve-focused modeling division of the international agency Wilhelmina Models.
  • 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_69b34544be3c819084d1ab82d29f90c5 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3501ef1388190b0c968b069014a59 completed March 12, 2026, 11:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b7b3b52c8190ae7c05448faf5558 completed March 14, 2026, 7:32 p.m.
Created at: March 12, 2026, 11:07 p.m.