Triple
T18705585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apache Parquet |
E457357
|
entity |
| Predicate | compressionCodec |
P27672
|
FINISHED |
| Object |
Brotli
Brotli is a modern, general-purpose lossless compression algorithm developed by Google, known for achieving high compression ratios and efficient web content delivery.
|
E1339014
|
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: Brotli | Statement: [Apache Parquet, compressionCodec, Brotli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brotli Context triple: [Apache Parquet, compressionCodec, Brotli]
-
A.
Zstandard
Zstandard is a fast, modern lossless data compression algorithm developed by Facebook that offers high compression ratios with low CPU usage.
-
B.
zlib
zlib is a widely used software library that provides lossless data compression using the DEFLATE algorithm.
-
C.
bzip2
bzip2 is a free and open-source data compression program known for its high compression ratios using the Burrows–Wheeler algorithm.
-
D.
gzip
gzip is a widely used GNU file compression utility that reduces file size using the DEFLATE algorithm, commonly producing .gz archives on Unix-like systems.
-
E.
Huffman
Huffman is a surname most commonly associated with the American computer scientist David A. Huffman, known for developing Huffman coding in information theory and data compression.
- 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: Brotli Triple: [Apache Parquet, compressionCodec, Brotli]
Generated description
Brotli is a modern, general-purpose lossless compression algorithm developed by Google, known for achieving high compression ratios and efficient web content delivery.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brotli Target entity description: Brotli is a modern, general-purpose lossless compression algorithm developed by Google, known for achieving high compression ratios and efficient web content delivery.
-
A.
Zstandard
Zstandard is a fast, modern lossless data compression algorithm developed by Facebook that offers high compression ratios with low CPU usage.
-
B.
zlib
zlib is a widely used software library that provides lossless data compression using the DEFLATE algorithm.
-
C.
bzip2
bzip2 is a free and open-source data compression program known for its high compression ratios using the Burrows–Wheeler algorithm.
-
D.
gzip
gzip is a widely used GNU file compression utility that reduces file size using the DEFLATE algorithm, commonly producing .gz archives on Unix-like systems.
-
E.
Huffman
Huffman is a surname most commonly associated with the American computer scientist David A. Huffman, known for developing Huffman coding in information theory and data compression.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671717b88190974f542015f641e8 |
completed | April 19, 2026, 11:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a052b3a95888190b09328d459164071 |
completed | May 14, 2026, 1:54 a.m. |
| NEDg | Description generation | batch_6a052dec70cc8190b66909ce6225b2bb |
completed | May 14, 2026, 2:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a052edba614819084d818fe1cc84ca4 |
completed | May 14, 2026, 2:09 a.m. |
Created at: April 10, 2026, 11:49 a.m.