Triple
T4443260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SparseArrays |
E96220
|
entity |
| Predicate | definesType |
P56536
|
FINISHED |
| Object |
Bidiagonal
Bidiagonal is a special kind of sparse matrix that has nonzero entries only on the main diagonal and either the superdiagonal or subdiagonal, making it efficient for numerical linear algebra computations.
|
E440653
|
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: Bidiagonal | Statement: [SparseArrays, definesType, Bidiagonal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bidiagonal Context triple: [SparseArrays, definesType, Bidiagonal]
-
A.
Binarowa
Binarowa is a village in southern Poland known for its historic wooden architecture and cultural heritage, including the UNESCO-listed St. Michael the Archangel Church.
-
B.
BDF
The BDF is the national military organization of the Kingdom of Bahrain, responsible for the country's defense and security.
-
C.
BIF
BIF is the National Rail station code for Barrow-in-Furness railway station in Cumbria, England.
-
D.
Bilayn
Bilayn is an alternative name for Bilen, likely referring to the same person, place, or entity under a different spelling or transliteration.
-
E.
Betti
Betti is a German diminutive given name, commonly used as a short form of Bettina.
- 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: Bidiagonal Triple: [SparseArrays, definesType, Bidiagonal]
Generated description
Bidiagonal is a special kind of sparse matrix that has nonzero entries only on the main diagonal and either the superdiagonal or subdiagonal, making it efficient for numerical linear algebra computations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bidiagonal Target entity description: Bidiagonal is a special kind of sparse matrix that has nonzero entries only on the main diagonal and either the superdiagonal or subdiagonal, making it efficient for numerical linear algebra computations.
-
A.
Binarowa
Binarowa is a village in southern Poland known for its historic wooden architecture and cultural heritage, including the UNESCO-listed St. Michael the Archangel Church.
-
B.
BDF
The BDF is the national military organization of the Kingdom of Bahrain, responsible for the country's defense and security.
-
C.
BIF
BIF is the National Rail station code for Barrow-in-Furness railway station in Cumbria, England.
-
D.
Bilayn
Bilayn is an alternative name for Bilen, likely referring to the same person, place, or entity under a different spelling or transliteration.
-
E.
Betti
Betti is a German diminutive given name, commonly used as a short form of Bettina.
- 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_69b345415ba481908df738e7174448ba |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3564216b081908c41109100b36862 |
completed | March 13, 2026, 12:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b61382d00481908b7c84f337b5cad7 |
completed | March 15, 2026, 2:03 a.m. |
| NEDg | Description generation | batch_69b6177d1a588190991fddf506239d22 |
completed | March 15, 2026, 2:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b61b6bc1448190b30d444a821bb1a5 |
completed | March 15, 2026, 2:37 a.m. |
Created at: March 12, 2026, 11:32 p.m.