Triple
T19125198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Special Forces |
E468158
|
entity |
| Predicate | typicalSubunitSize |
P106613
|
FINISHED |
| Object | 12 soldiers |
—
|
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: 12 soldiers | Statement: [United States Special Forces, typicalSubunitSize, 12 soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSubunitSize Context triple: [United States Special Forces, typicalSubunitSize, 12 soldiers]
-
A.
typicalSubunitOf
Indicates that something is a standard or commonly occurring subcomponent or part of a larger whole.
-
B.
typicalUnitSize
Indicates the standard or most common size or quantity in which something is typically measured, packaged, or used.
-
C.
subunitType
Indicates that one entity is a specific kind or classification of subunit within the structure or composition of another entity.
-
D.
typicalUnitType
Indicates that one entity is the standard or commonly used unit type associated with measuring or expressing the other entity.
-
E.
divisionSize
chosen
Indicates the size or magnitude of a division or subdivided part in relation to a whole.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3cc5ba08190a1073f2836caf5d3 |
completed | April 20, 2026, 8:29 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b085288190b974d649e12e0844 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.