Triple
T25689222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashihara-no-Nakatsukuni |
E644152
|
entity |
| Predicate | hasDomainBelow |
P12702
|
FINISHED |
| Object | Yomi |
—
|
NE NERFINISHED |
How this triple was built (2 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: Yomi | Statement: [Ashihara-no-Nakatsukuni, hasDomainBelow, Yomi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDomainBelow Context triple: [Ashihara-no-Nakatsukuni, hasDomainBelow, Yomi]
-
A.
hasDomainAbove
Indicates that one entity’s domain or scope is positioned higher or supersedes another entity’s domain in a hierarchical or layered structure.
-
B.
existsBelow
chosen
Indicates that at least one instance of an entity is located or occurs at a lower level or position relative to another entity.
-
C.
hasSubdomain
Indicates that one domain is a subordinate or nested part of another domain within a hierarchical naming structure.
-
D.
containsDomain
Indicates that one entity includes or encompasses a specific domain as part of its scope, structure, or area of applicability.
-
E.
hasSmallerDomainOfUse
Indicates that the range or scope in which one entity can be used is more limited or restricted than that of another entity.
- F. None of above.
Provenance (3 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_69e77e8046888190b07ffa58c7e2c37a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f600c18a14819081b5914dd3b0f9cf |
completed | May 2, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 21, 2026, 8:14 p.m.