Triple
T8118263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Digital Research, Inc. |
E189534
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | GEM |
E713567
|
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: GEM | Statement: [Digital Research, Inc., notableWork, GEM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GEM Context triple: [Digital Research, Inc., notableWork, GEM]
-
A.
GEM
GEM is the Growth Enterprise Market board of the Hong Kong Stock Exchange, designed for smaller, high-growth and emerging companies to raise capital.
-
B.
GEM
chosen
GEM (Graphics Environment Manager) is a graphical user interface and desktop environment developed by Digital Research in the 1980s, best known for bringing a Macintosh-like windowed interface to DOS-based personal computers and the Atari ST.
-
C.
GEML
GEML is the ICAO airport code assigned to Melilla Airport in the Spanish autonomous city of Melilla.
-
D.
GeMS
GeMS is a multi-conjugate adaptive optics system used on large telescopes to correct atmospheric distortion and produce sharper astronomical images.
-
E.
Gem
Gem is the short-form name for CBC Gem, the Canadian Broadcasting Corporation’s online streaming service for television shows, movies, and live content.
- 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_69ca82baad008190ab2859712b9b1607 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4358e1688190940b98114225113b |
completed | March 31, 2026, 3:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cced122cf08190b9cf17c3055e5431 |
completed | April 1, 2026, 10:01 a.m. |
Created at: March 30, 2026, 5:33 p.m.