Triple
T19755922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eleanor J. Gibson |
E474499
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Principles of Perceptual Learning and Development |
—
|
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: Principles of Perceptual Learning and Development | Statement: [Eleanor J. Gibson, notableWork, Principles of Perceptual Learning and Development]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Principles of Perceptual Learning and Development Context triple: [Eleanor J. Gibson, notableWork, Principles of Perceptual Learning and Development]
-
A.
Gibsonian theory of perceptual learning
chosen
The Gibsonian theory of perceptual learning is a psychological framework proposing that perception improves through direct interaction with the environment, as individuals learn to detect increasingly subtle and useful information (or "invariants") in sensory input without relying on internal representations.
-
B.
An interactive activation model of context effects in letter perception
"An interactive activation model of context effects in letter perception" is a seminal cognitive psychology paper that introduced a computational model explaining how letter and word recognition are influenced by both bottom-up sensory input and top-down contextual information.
-
C.
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information is a seminal 1982 book by David Marr that laid the foundations of computational neuroscience and modern theories of visual perception.
-
D.
Learning to See
"Learning to See" is an autobiographical essay by Eudora Welty that reflects on how her early experiences and observations shaped her development as a writer.
-
E.
The Psychology of Computer Vision (edited volume)
The Psychology of Computer Vision is an influential edited volume, compiled by Patrick Henry Winston, that brings together foundational research exploring how principles of human perception and cognition can inform and advance computer vision.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6531afcbc8190bd5364700008f6d8 |
completed | April 20, 2026, 4:23 p.m. |
Created at: April 10, 2026, 1:48 p.m.