Triple
T3358152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 509th Composite Group |
E70653
|
entity |
| Predicate | unitSize |
P3664
|
FINISHED |
| Object | approximately 1,800 personnel |
—
|
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: approximately 1,800 personnel | Statement: [509th Composite Group, unitSize, approximately 1,800 personnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unitSize Context triple: [509th Composite Group, unitSize, approximately 1,800 personnel]
-
A.
typicalUnitSize
chosen
Indicates the standard or most common size or quantity in which something is typically measured, packaged, or used.
-
B.
minimumUnitSize
Indicates that there is a smallest allowable or defined size or quantity for the unit involved in the relationship.
-
C.
cellSize
Indicates the physical dimensions or volume of a cell in a biological or computational context.
-
D.
sizeDefinedBy
Indicates that the size or magnitude of one entity is determined, constrained, or specified by another entity.
-
E.
stateSize
Indicates the relative or absolute physical extent or dimensions of a state, such as its area or population size.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb26523cc819091006fde7beb32e4 |
completed | March 8, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.