Triple
T12727874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Colored Troops |
E304152
|
entity |
| Predicate | numberOfRegiments |
P91944
|
FINISHED |
| Object | over 160 |
—
|
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: over 160 | Statement: [United States Colored Troops, numberOfRegiments, over 160]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfRegiments Context triple: [United States Colored Troops, numberOfRegiments, over 160]
-
A.
numberOfRegimentsInvolved
chosen
Indicates the total count of regiments that participated in or were involved in a specified event or action.
-
B.
numberOfBattalions
Indicates the quantitative relationship specifying how many battalions are associated with a given entity or context.
-
C.
regimentalCategory
Indicates the classification or type of regiment to which a military unit or formation belongs.
-
D.
typeOfTroops
Indicates the specific category or kind of military forces involved in or associated with an entity or event.
-
E.
regimentalFamily
Indicates a familial or close-kin relationship that exists within, or is defined by, a shared regimental or military unit affiliation.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96d89ea70819098c470344f172167 |
completed | April 10, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69d96403957c81909acdee7bdae71696 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:25 p.m.