Triple
T14936349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walleye |
E372401
|
entity |
| Predicate | supportsGoogleService |
P39530
|
FINISHED |
| Object | Google Lens |
E35328
|
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: Google Lens | Statement: [Walleye, supportsGoogleService, Google Lens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Google Lens Context triple: [Walleye, supportsGoogleService, Google Lens]
-
A.
Google Lens
chosen
Google Lens is an image recognition and search tool by Google that uses artificial intelligence to identify objects, text, and scenes from a device’s camera or photos and provide relevant information or actions.
-
B.
Google Vision API
Google Vision API is a cloud-based image analysis service that uses machine learning to detect objects, text, faces, and other visual features within images.
-
C.
Bixby Vision
Bixby Vision is Samsung’s image-recognition and augmented reality feature that lets users identify objects, translate text, and obtain contextual information through their device’s camera.
-
D.
Reckonize
Reckonize is a music producer known for creating tracks such as "Uncontrolled Substance."
-
E.
Britannica ImageQuest
Britannica ImageQuest is a curated educational image database offering millions of rights-cleared photos and illustrations for teaching and learning.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded647ae388190a0e97c03f2a4d832 |
completed | April 15, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e8e9c0c81909cfb1e02987527c0 |
completed | May 9, 2026, 12:23 a.m. |
Created at: April 10, 2026, 2:37 a.m.