Triple
T6033915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ROOT |
E134370
|
entity |
| Predicate | hasComponent |
P35
|
FINISHED |
| Object | TCanvas |
E322645
|
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: TCanvas | Statement: [ROOT, hasComponent, TCanvas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: TCanvas Context triple: [ROOT, hasComponent, TCanvas]
-
A.
TCanvas
chosen
TCanvas is a core VCL graphics class in Delphi used for drawing text, shapes, and images onto windows, controls, printers, and bitmaps.
-
B.
TPanel
TPanel is a container control in Delphi's Visual Component Library used to group and organize other visual components on a form.
-
C.
TImage
TImage is a VCL component in Delphi used to display and manipulate images within graphical user interfaces.
-
D.
ROOT
ROOT is a widely used object-oriented data analysis framework and file format developed at CERN for storing, processing, and visualizing large volumes of high-energy physics data.
-
E.
Web Graphics Library
Web Graphics Library is a JavaScript API that enables rendering interactive 2D and 3D graphics within web browsers using the GPU without the need for plug-ins.
- 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_69c0087515148190a97475d412563865 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c056b220608190b156be95632cf3b3 |
completed | March 22, 2026, 8:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11388aec881908408d5844c96ea2d |
completed | March 23, 2026, 10:18 a.m. |
Created at: March 22, 2026, 4:08 p.m.