Triple
T31112749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nakajima |
E792995
|
entity |
| Predicate | militaryCustomer |
P181073
|
FINISHED |
| Object | Imperial Japanese Navy Air Service |
—
|
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: Imperial Japanese Navy Air Service | Statement: [Nakajima, militaryCustomer, Imperial Japanese Navy Air Service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryCustomer Context triple: [Nakajima, militaryCustomer, Imperial Japanese Navy Air Service]
-
A.
notableMilitaryCustomer
Indicates that an entity is a significant or prominent purchaser or client of a military organization or defense-related supplier.
-
B.
militaryUse
Indicates the use of something (such as land, facilities, equipment, or resources) for military purposes or operations.
-
C.
countryMilitary
Indicates that a country possesses, controls, or is associated with a particular military force or armed organization.
-
D.
militaryBacked
Indicates that one entity is supported, protected, or sustained by the military power or armed forces of another entity.
-
E.
militarySystem
Indicates a relationship where an entity functions as, belongs to, or is characterized by a particular military organizational or operational system.
- 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_69f224cfd5d881908ec6447bc321cd58 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f760a35b988190904e6267553ad2fe |
completed | May 3, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69f75eb3d6f081908c933474eb359e3d |
completed | May 3, 2026, 2:41 p.m. |
| PDg | Predicate description generation | batch_69f760a2a90c8190b8fbc55412ab752b |
completed | May 3, 2026, 2:50 p.m. |
Created at: April 29, 2026, 9:04 p.m.