Triple
T29100683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yakuza |
E736632
|
entity |
| Predicate | developedByDivision |
P32488
|
FINISHED |
| Object |
Ryu Ga Gotoku Studio
Ryu Ga Gotoku Studio is a Japanese video game development team at Sega best known for creating and overseeing the long-running Yakuza (Like a Dragon) action-adventure game series.
|
E1850762
|
NE FINISHED |
How this triple was built (3 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: Ryu Ga Gotoku Studio | Statement: [Yakuza, developedByDivision, Ryu Ga Gotoku Studio]
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: Ryu Ga Gotoku Studio Triple: [Yakuza, developedByDivision, Ryu Ga Gotoku Studio]
Generated description
Ryu Ga Gotoku Studio is a Japanese video game development team at Sega best known for creating and overseeing the long-running Yakuza (Like a Dragon) action-adventure game series.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developedByDivision Context triple: [Yakuza, developedByDivision, Ryu Ga Gotoku Studio]
-
A.
isDevelopedBy
chosen
Indicates that something (such as a product, project, or idea) is created, produced, or brought into existence through the work or effort of a particular developer or group of developers.
-
B.
developedAs
Indicates that one entity was created, designed, or evolved specifically to function as or replace another entity.
-
C.
developmentLedBy
Indicates that the development of something is directed, managed, or overseen by a particular agent or entity.
-
D.
featuredDivision
Indicates that one division is highlighted or given special prominence in relation to others within a particular context.
-
E.
formerlyDevelopedBy
Indicates that an entity was developed in the past by another entity, but is no longer developed by that same party.
- F. None of above.
Provenance (6 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f7117e55908190a67105e92bc4830f |
completed | May 3, 2026, 9:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2537b8df3c8190b138ae96e4ef85c7 |
completed | June 7, 2026, 9:19 a.m. |
| NEDg | Description generation | batch_6a2542e78e108190a7ead54421361eab |
completed | June 7, 2026, 10:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a254363ba088190b6f0b18f68d43add |
completed | June 7, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69f70f380690819090cc34763ba460ed |
completed | May 3, 2026, 9:02 a.m. |
Created at: April 28, 2026, 11:11 a.m.