Triple

T18973708
Position Surface form Disambiguated ID Type / Status
Subject Private Robert E. Lee Prewitt E464237 entity
Predicate familyName P18 FINISHED
Object Prewitt 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: Prewitt | Statement: [Private Robert E. Lee Prewitt, familyName, Prewitt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prewitt
Context triple: [Private Robert E. Lee Prewitt, familyName, Prewitt]
  • A. Prewitt chosen
    Prewitt is a surname of English origin borne by various notable individuals across fields such as academia, politics, and the arts.
  • B. Sobel
    Sobel is a surname most notably associated with American science writer Dava Sobel, known for her popular books on the history of science and astronomy.
  • C. Harris corner detector
    The Harris corner detector is a foundational computer vision algorithm used to identify interest points or corners in images for tasks like tracking, matching, and 3D reconstruction.
  • D. Gabor filter
    A Gabor filter is a linear filter used in image processing and computer vision that analyzes spatial frequency content in specific directions and scales, making it useful for texture analysis and feature extraction.
  • E. Shi–Tomasi corner detector
    The Shi–Tomasi corner detector is a computer vision algorithm that identifies good feature points (corners) in images for robust tracking and recognition tasks.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d61d7728819096f0baea75658a6a completed April 20, 2026, 7:30 a.m.
Created at: April 10, 2026, noon