Triple
T9000828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CRT |
E215033
|
entity |
| Predicate | supersededBy |
P101
|
FINISHED |
| Object | LCD |
E409716
|
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: LCD | Statement: [CRT, supersededBy, LCD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LCD Context triple: [CRT, supersededBy, LCD]
-
A.
LCD TV
chosen
An LCD TV is a flat-panel television that uses liquid crystal display technology with a backlight to produce images, widely known for its affordability and broad market presence compared to newer display types.
-
B.
DLP technology
DLP technology is a digital display and projection system that uses microscopic mirrors to modulate light and create high-quality images in projectors and related devices.
-
C.
VDU
VDU is the Lithuanian abbreviation for Vytautas Magnus University, a prominent public university in Kaunas, Lithuania.
-
D.
E Ink
E Ink is a low-power electronic paper display technology that mimics the appearance of ink on paper and is widely used in e-readers and other devices requiring high readability.
-
E.
LCDGT
LCDGT is the standard controlled vocabulary developed by the Library of Congress to describe demographic characteristics of creators and contributors in library and archival metadata.
- 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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6954bb1881908d004a26ba7fe360 |
completed | April 1, 2026, 12:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0d987dc81908f1d74f390f18a9c |
completed | April 3, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:05 p.m.