Triple
T615763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple Lisa |
E14399
|
entity |
| Predicate | graphics |
P17160
|
FINISHED |
| Object | black-and-white display |
—
|
LITERAL 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: black-and-white display | Statement: [Apple Lisa, graphics, black-and-white display]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: graphics Context triple: [Apple Lisa, graphics, black-and-white display]
-
A.
draws
Indicates that one entity creates a visual representation or image of another entity.
-
B.
visualizationLibrary
Indicates that an entity uses, depends on, or is implemented with a particular visualization library for rendering or displaying visual data.
-
C.
illustrator
Indicates that one entity serves as the illustrator (creator of visual artwork or drawings) for another entity, such as a book, article, or other work.
-
D.
architecture
Indicates the structural design or organizational framework that defines how components of a system or entity are arranged and interact.
-
E.
iconographyFeature
Indicates a visual element or motif that appears as a distinct feature within a work’s iconography.
- F. None of above. chosen
Provenance (4 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e0b438881909ad515adf7a4eb79 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49cfbcbf88190a854921dc531eba8 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49def31ec81909dc53e70f4a36eda |
completed | March 1, 2026, 8:13 p.m. |
Created at: March 1, 2026, 7:35 p.m.