Triple
T19620820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 3rd Battalion, 28th Marines |
E471000
|
entity |
| Predicate | standardSubunit |
P112029
|
FINISHED |
| Object | rifle company |
—
|
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: rifle company | Statement: [3rd Battalion, 28th Marines, standardSubunit, rifle company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardSubunit Context triple: [3rd Battalion, 28th Marines, standardSubunit, rifle company]
-
A.
typicalSubunitOf
chosen
Indicates that something is a standard or commonly occurring subcomponent or part of a larger whole.
-
B.
basicUnitOf
Indicates that one entity serves as the fundamental or smallest constituent unit from which the other entity is composed or defined.
-
C.
minorUnitSubdivisions
Indicates that one administrative or organizational unit is subdivided into smaller, subordinate units.
-
D.
minorUnitUsage
Indicates how a minor or subordinate unit is used or functions in relation to a larger or primary unit.
-
E.
superunitOf
Indicates that one unit is hierarchically above and directly encompasses another unit within an organizational or structural system.
- 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e668408190bc1e12a336b0687b |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:43 p.m.