Triple
T35755635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kagi |
E1033438
|
entity |
| Predicate | countryDuringNameUsage |
P203781
|
FINISHED |
| Object | Empire of Japan |
E657239
|
NE 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: Empire of Japan | Statement: [Kagi, countryDuringNameUsage, Empire of Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryDuringNameUsage Context triple: [Kagi, countryDuringNameUsage, Empire of Japan]
-
A.
hasNameUsageCountry
Indicates that a particular name is used or recognized within a specified country.
-
B.
laterNameOfCountry
Indicates that the referenced entity is a later or subsequent name adopted by a country that previously had a different name.
-
C.
countryOfNamingTradition
Indicates the country whose cultural or linguistic naming conventions are used to form or interpret a given name.
-
D.
countryNameUsage
Indicates how a country’s name is used or applied in a particular context or representation.
-
E.
eraNameUsedInDocuments
Indicates that a particular era name is used as a temporal reference in the specified documents.
- F. None of above. chosen
Provenance (5 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a02008fcf1c8190b5b6c285944c52e9 |
completed | May 11, 2026, 4:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3885f6c748819098140083c0bc95e3 |
completed | June 22, 2026, 12:46 a.m. |
| PD | Predicate disambiguation | batch_6a01ffd3ba008190b6f026bd4e6b9a37 |
completed | May 11, 2026, 4:12 p.m. |
| PDg | Predicate description generation | batch_6a02008eb6ac81908f66e8e07e0726c6 |
completed | May 11, 2026, 4:15 p.m. |
Created at: May 3, 2026, 4:06 p.m.