Triple
T21936484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 6th Marine Division (United States) |
E541700
|
entity |
| Predicate | missionAfterWar |
P33202
|
FINISHED |
| Object | occupation duty in northern China |
—
|
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: occupation duty in northern China | Statement: [6th Marine Division (United States), missionAfterWar, occupation duty in northern China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: missionAfterWar Context triple: [6th Marine Division (United States), missionAfterWar, occupation duty in northern China]
-
A.
missionPhaseAfter
Indicates that one mission phase occurs later in sequence or time than another mission phase.
-
B.
operatorAfterWar
Indicates that one entity serves or functions as an operator after the occurrence or end of a war.
-
C.
goalDuringWar
Indicates that a particular goal or objective is pursued, exists, or is relevant during the time period of a war or armed conflict.
-
D.
missionField
chosen
Indicates a relationship where an entity’s work, activity, or purpose is directed toward a particular area, domain, or target context as its mission focus.
-
E.
usedAfterWar
Indicates that an entity came into use only after a specific war or conflict had ended.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1241c909c81908644eb73baa9def1 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:54 p.m.