Triple
T17727359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Udaijin |
E442496
|
entity |
| Predicate | rankRelativeToOtherOffices |
P22893
|
FINISHED |
| Object | below Daijō-daijin |
—
|
LITERAL FINISHED |
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: below Daijō-daijin | Statement: [Udaijin, rankRelativeToOtherOffices, below Daijō-daijin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankRelativeToOtherOffices Context triple: [Udaijin, rankRelativeToOtherOffices, below Daijō-daijin]
-
A.
rankWithinOrganization
Indicates the relative hierarchical position or level an entity holds within a specific organization.
-
B.
rankComparedTo
chosen
Indicates the relative ordering or position of one entity in comparison to another based on a specified ranking criterion.
-
C.
hasRelativeInOffice
Indicates that one entity has a family member who holds or held a particular office or official position.
-
D.
numberOfOffices
Indicates the total count of offices associated with a given entity.
-
E.
comparableOffice
Indicates that two offices are sufficiently similar in relevant characteristics (such as size, function, or status) to be meaningfully compared to each other.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e478e3cb708190b47456ad2008a65e |
completed | April 19, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69e3cde815e08190881972e2d80d151e |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:07 a.m.