Triple
T30373133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarakan operation |
E772604
|
entity |
| Predicate | combatantAxis |
P117522
|
FINISHED |
| Object | Imperial Japanese Army |
—
|
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 Army | Statement: [Tarakan operation, combatantAxis, Imperial Japanese Army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combatantAxis Context triple: [Tarakan operation, combatantAxis, Imperial Japanese Army]
-
A.
enemyDuringWWII
Indicates that one entity was an enemy of the other during World War II.
-
B.
warAdversary
chosen
Indicates that two entities are opponents or enemies engaged in a state of war or armed conflict.
-
C.
commanderDuringWorldWarII
Indicates that one entity served as a commander of the other specifically during the period of World War II.
-
D.
combatantRoleOfGermany
Indicates that the specified role is one that Germany held as a combatant in a particular conflict or war.
-
E.
battleStarsWorldWarII
Indicates that the entity has received battle stars for participation in World War II military operations.
- 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_69f2248d71408190aec0d5c2001b1cff |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 7:59 p.m.