Triple
T12253455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andaandi |
E292034
|
entity |
| Predicate | iso6393Code |
P36930
|
FINISHED |
| Object |
dgl
dgl is the ISO 639-3 language code for Andaandi, a Nubian language spoken primarily in parts of Sudan.
|
E972585
|
NE FINISHED |
How this triple was built (4 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: dgl | Statement: [Andaandi, iso6393Code, dgl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: dgl Context triple: [Andaandi, iso6393Code, dgl]
-
A.
DGL
DGL is the vehicle registration code assigned to the town of Głogów in Poland.
-
B.
EGCN
EGCN is the ICAO airport code for Doncaster Sheffield Airport, a former international airport in South Yorkshire, England.
-
C.
DAG
DAG is the National Rail station code for Dalgety Bay railway station in Fife, Scotland.
-
D.
GraphX
GraphX is Apache Spark’s distributed graph processing framework that enables large-scale graph computation and analysis using Spark’s resilient distributed datasets (RDDs).
-
E.
cuGraph
cuGraph is a GPU-accelerated graph analytics library in the NVIDIA RAPIDS ecosystem designed to perform large-scale graph processing and algorithms efficiently on NVIDIA GPUs.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: dgl Triple: [Andaandi, iso6393Code, dgl]
Generated description
dgl is the ISO 639-3 language code for Andaandi, a Nubian language spoken primarily in parts of Sudan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: dgl Target entity description: dgl is the ISO 639-3 language code for Andaandi, a Nubian language spoken primarily in parts of Sudan.
-
A.
DGL
DGL is the vehicle registration code assigned to the town of Głogów in Poland.
-
B.
EGCN
EGCN is the ICAO airport code for Doncaster Sheffield Airport, a former international airport in South Yorkshire, England.
-
C.
DAG
DAG is the National Rail station code for Dalgety Bay railway station in Fife, Scotland.
-
D.
GraphX
GraphX is Apache Spark’s distributed graph processing framework that enables large-scale graph computation and analysis using Spark’s resilient distributed datasets (RDDs).
-
E.
cuGraph
cuGraph is a GPU-accelerated graph analytics library in the NVIDIA RAPIDS ecosystem designed to perform large-scale graph processing and algorithms efficiently on NVIDIA GPUs.
- F. None of above. chosen
Provenance (5 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cc849308190b6ff416f8b4f01e8 |
completed | April 10, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60abdc5988190a19104385f54fb06 |
completed | May 2, 2026, 2:31 p.m. |
| NEDg | Description generation | batch_69f60d8456d881908b5647b77fc53780 |
completed | May 2, 2026, 2:43 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f60e2c52b0819094c8e67286235400 |
completed | May 2, 2026, 2:46 p.m. |
Created at: April 8, 2026, 9:52 p.m.