Triple
T35800405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 利根川 |
E1034958
|
entity |
| Predicate | 歴史的事象 |
P2107
|
FINISHED |
| Object | 利根川東遷事業により流路が変えられた |
—
|
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: 利根川東遷事業により流路が変えられた | Statement: [利根川, 歴史的事象, 利根川東遷事業により流路が変えられた]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 歴史的事象 Context triple: [利根川, 歴史的事象, 利根川東遷事業により流路が変えられた]
-
A.
歴史
Indicates a relationship where something pertains to, records, or is involved in the events, development, or study of the past over time.
-
B.
hasHistoricalEvent
chosen
Indicates that a historical event occurred in, is associated with, or is relevant to a particular entity.
-
C.
historicalEventsDescribed
Indicates that one entity (such as a document, text, or account) describes or recounts the historical events associated with another entity.
-
D.
historicalIssue
Indicates that one entity is a past or previously existing edition, version, or instance of another entity, typically within a chronological sequence.
-
E.
historical
Indicates that the subject has existed, occurred, or been relevant in the past rather than in the present or future.
- 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_69f76e169bd081909f16cd8c9ee7870c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a258a1a88190ad421d43295d376c |
completed | May 3, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.