Triple
T27488196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 広田弘毅 |
E693800
|
entity |
| Predicate | 駐在経験国 |
P138376
|
FINISHED |
| Object | 韓国 |
—
|
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: 韓国 | Statement: [広田弘毅, 駐在経験国, 韓国]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 駐在経験国 Context triple: [広田弘毅, 駐在経験国, 韓国]
-
A.
countryOfExperience
chosen
Indicates that an entity has gained experience (such as work, study, or professional activity) within the specified country.
-
B.
visitedCountry
Indicates that an entity has traveled to and spent time in a particular country.
-
C.
hasCountry
Indicates that one entity possesses, is associated with, or is located within a specific country.
-
D.
countryOfMission
Indicates that an entity (such as a mission, project, or operation) is associated with or takes place in a particular country.
-
E.
visitedConstituentCountry
Indicates that one entity has traveled to and spent time in a country that is part of a larger sovereign state or political union.
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6359e3d3c81909814e2f0a7fb0ea9 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f631871c888190bf29466fe4254e51 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 1:03 p.m.