Triple
T20399673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indigo R3000 models |
E500296
|
entity |
| Predicate | graphicsAPI |
P22768
|
FINISHED |
| Object | IRIS GL (historically) |
—
|
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: IRIS GL (historically) | Statement: [Indigo R3000 models, graphicsAPI, IRIS GL (historically)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IRIS GL (historically) Context triple: [Indigo R3000 models, graphicsAPI, IRIS GL (historically)]
-
A.
IRIS GL
chosen
IRIS GL is an early proprietary 3D graphics application programming interface developed by Silicon Graphics that served as a precursor to OpenGL.
-
B.
IRIS-B
IRIS-B was a European Space Research Organisation scientific satellite used primarily for studying solar and cosmic X-ray and gamma-ray emissions in Earth orbit.
-
C.
IRS-1D
IRS-1D is an Indian remote sensing satellite in the IRS series used primarily for Earth observation and resource monitoring.
-
D.
IR-20
IR-20 is the ISO 3166-2 subdivision code assigned to Iran’s Semnan Province.
-
E.
Iris Law
Iris Law is a British model and actress known for her high-fashion campaigns and emerging film roles, as well as being the daughter of actors Jude Law and Sadie Frost.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798db79c819085e3a2526538726f |
completed | April 20, 2026, 7:07 p.m. |
Created at: April 16, 2026, 11:29 a.m.