Triple
T35447020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 土佐国高知 |
E1024514
|
entity |
| Predicate | wasCenterOfDomain |
P162376
|
FINISHED |
| Object |
土佐藩
土佐藩 was a powerful feudal domain of Japan’s Edo period, ruled by the Yamauchi clan and later known for producing key leaders of the Meiji Restoration such as Sakamoto Ryōma.
|
E2142242
|
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: 土佐藩 | Statement: [土佐国高知, wasCenterOfDomain, 土佐藩]
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: 土佐藩 Triple: [土佐国高知, wasCenterOfDomain, 土佐藩]
Generated description
土佐藩 was a powerful feudal domain of Japan’s Edo period, ruled by the Yamauchi clan and later known for producing key leaders of the Meiji Restoration such as Sakamoto Ryōma.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasCenterOfDomain Context triple: [土佐国高知, wasCenterOfDomain, 土佐藩]
-
A.
laterDomainCenter
Indicates that one domain center occurs at a later time or stage than another domain center within a given context.
-
B.
isCentreOf
Indicates that one entity serves as the central point, core, or focal location relative to another entity or context.
-
C.
partOfDomain
Indicates that one entity belongs to, is included within, or is a constituent part of the scope or domain defined by another entity.
-
D.
centerIs
Indicates that one entity serves as the central point or middle position of another entity or space.
-
E.
domainCenter
chosen
Indicates that something is located at or serves as the central point or core area of a specified domain or region.
- 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_69f76df8089481909f0018266ee881b7 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38402d44c48190b6288df4115342ee |
completed | June 21, 2026, 7:49 p.m. |
| NEDg | Description generation | batch_6a3841a972e8819090d7e0a6d0f10aac |
completed | June 21, 2026, 7:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a38420fb2a88190ac17badf0bfc5b6c |
completed | June 21, 2026, 7:57 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:04 p.m.