Triple
T37061522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 宇治川 |
E917336
|
entity |
| Predicate | 合流後の名称 |
P187301
|
FINISHED |
| Object | 淀川 |
—
|
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: 淀川 | Statement: [宇治川, 合流後の名称, 淀川]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 合流後の名称 Context triple: [宇治川, 合流後の名称, 淀川]
-
A.
consolidatedUnder
Indicates that one entity has been merged into and is now formally part of another, typically larger or parent, entity.
-
B.
consolidatedAfter
Indicates that one entity was formed or unified as a result of merging or combining multiple entities after a specified point in time.
-
C.
mainlandNameAfterUnion
Indicates that the predicate links an entity to the name used for its mainland territory after a political or administrative union has taken place.
-
D.
reunifiedAs
Indicates that entities which were previously separated or divided have been brought back together into a single unified whole.
-
E.
wasUnifiedWith
Indicates that two or more previously separate entities were brought together to form a single unified whole.
- F. None of above. chosen
Provenance (4 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_69f76e95fa40819091e14681087ae5e4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb34e5576881909394355c8ec6ddd2 |
completed | May 6, 2026, 12:32 p.m. |
| PD | Predicate disambiguation | batch_69fb2f6171e88190bf1e0ee6a644b6a9 |
completed | May 6, 2026, 12:09 p.m. |
| PDg | Predicate description generation | batch_69fb34e4906c8190abb1c293fb84329a |
completed | May 6, 2026, 12:32 p.m. |
Created at: May 3, 2026, 4:14 p.m.