Triple
T8163080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TokuDB |
E190622
|
entity |
| Predicate | developedBy |
P73
|
FINISHED |
| Object |
Tokutek
Tokutek was a software company best known for creating high-performance storage engines for MySQL and MariaDB, particularly the fractal tree–based TokuDB.
|
E715757
|
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: Tokutek | Statement: [TokuDB, developedBy, Tokutek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokutek Context triple: [TokuDB, developedBy, Tokutek]
-
A.
Kiwi Enterprises
Kiwi Enterprises was a software company best known for its network management and logging tools before being acquired by SolarWinds.
-
B.
Pando Company
Pando Company is a film production company known for producing the movie "The Happy Ending."
-
C.
Sogeti
Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
-
D.
Rossum Corporation
Rossum Corporation is a powerful and morally dubious tech conglomerate in the TV series "Dollhouse," responsible for the mind-wiping and imprinting technology used to control human "dolls."
-
E.
Northesk
Northesk is the territorial designation associated with the Scottish peerage title Earl of Northesk, historically linked to the Carnegie family.
- 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: Tokutek Triple: [TokuDB, developedBy, Tokutek]
Generated description
Tokutek was a software company best known for creating high-performance storage engines for MySQL and MariaDB, particularly the fractal tree–based TokuDB.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tokutek Target entity description: Tokutek was a software company best known for creating high-performance storage engines for MySQL and MariaDB, particularly the fractal tree–based TokuDB.
-
A.
Kiwi Enterprises
Kiwi Enterprises was a software company best known for its network management and logging tools before being acquired by SolarWinds.
-
B.
Pando Company
Pando Company is a film production company known for producing the movie "The Happy Ending."
-
C.
Sogeti
Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
-
D.
Rossum Corporation
Rossum Corporation is a powerful and morally dubious tech conglomerate in the TV series "Dollhouse," responsible for the mind-wiping and imprinting technology used to control human "dolls."
-
E.
Northesk
Northesk is the territorial designation associated with the Scottish peerage title Earl of Northesk, historically linked to the Carnegie family.
- 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_69ca82c0ef14819083713f4473dd847c |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4557ebc88190b4e2cab258374d23 |
completed | March 31, 2026, 3:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf35000c8190ba78f69b7b1290e8 |
completed | April 1, 2026, 6:46 a.m. |
| NEDg | Description generation | batch_69ccc311d4e8819080f4aeef8ee7dc3b |
completed | April 1, 2026, 7:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ccd83115fc8190a3e276bed0a00926 |
completed | April 1, 2026, 8:32 a.m. |
Created at: March 30, 2026, 5:38 p.m.