Triple
T12573016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucas–Kanade optical flow algorithm |
E295649
|
entity |
| Predicate | commonVariant |
P4680
|
FINISHED |
| Object | inverse compositional Lucas–Kanade |
E295649
|
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: inverse compositional Lucas–Kanade | Statement: [Lucas–Kanade optical flow algorithm, commonVariant, inverse compositional Lucas–Kanade]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: inverse compositional Lucas–Kanade Context triple: [Lucas–Kanade optical flow algorithm, commonVariant, inverse compositional Lucas–Kanade]
-
A.
Lucas–Kanade optical flow algorithm
chosen
The Lucas–Kanade optical flow algorithm is a widely used computer vision method for estimating the motion of features between consecutive images by assuming locally constant motion and solving a least-squares problem.
-
B.
Kanade–Lucas–Tomasi feature tracker
The Kanade–Lucas–Tomasi feature tracker is a widely used computer vision algorithm for robustly tracking distinctive image features across video frames, building on the Lucas–Kanade optical flow method with Tomasi’s feature selection criteria.
-
C.
Ada Optical Flow Accelerator
The Ada Optical Flow Accelerator is a dedicated hardware engine in NVIDIA’s Ada Lovelace GPUs that rapidly computes high-quality motion vectors to enhance tasks like video processing, frame interpolation, and AI-powered motion analysis.
-
D.
Deep Fusion
Deep Fusion is an Apple computational photography technology that uses machine learning to combine multiple exposures for sharper, more detailed photos with improved texture and reduced noise.
-
E.
Scale Space
Scale Space is an innovation and scale-up hub located at Imperial College London's White City campus, designed to support high-growth technology and science businesses.
- 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_69d6ad9cac2c81908e8a7bed82d1e21d |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d954a52c788190beac128a97e34dc1 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65595826081908035655f7930f55a |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 8, 2026, 11:50 p.m.