Triple
T36563782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uesugi Kagekatsu |
E901914
|
entity |
| Predicate | laterKoku |
P116276
|
FINISHED |
| Object | 300,000 koku at Yonezawa |
—
|
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: 300,000 koku at Yonezawa | Statement: [Uesugi Kagekatsu, laterKoku, 300,000 koku at Yonezawa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterKoku Context triple: [Uesugi Kagekatsu, laterKoku, 300,000 koku at Yonezawa]
-
A.
laterIn
Indicates that one event, state, or time point occurs after another in temporal order.
-
B.
laterBase
Indicates that one event, state, or version occurs or is valid at a later time than another referenced event, state, or version.
-
C.
kokudaka
chosen
Indicates a relationship where a landholding or domain is assigned a value based on its assessed agricultural productivity or tax yield, typically measured in koku.
-
D.
laterSought
Indicates that one entity attempted to obtain, pursue, or request another entity at a subsequent time relative to some prior reference point.
-
E.
laterExtendedIn
Indicates that an existing entity (such as a work, version, or specification) was subsequently expanded, updated, or built upon by a later 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_69f76e634e9481908c9ba1b87ab87c26 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00b2b425a8819091ff65695e98c3af |
completed | May 10, 2026, 4:30 p.m. |
| PD | Predicate disambiguation | batch_6a00b06efa248190b2d16b4889185119 |
completed | May 10, 2026, 4:21 p.m. |
Created at: May 3, 2026, 4:11 p.m.