Triple
T7601219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Army Armor Branch |
E179986
|
entity |
| Predicate | officerBranchCode |
P9318
|
FINISHED |
| Object | 19A |
—
|
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: 19A | Statement: [United States Army Armor Branch, officerBranchCode, 19A]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officerBranchCode Context triple: [United States Army Armor Branch, officerBranchCode, 19A]
-
A.
hasOfficerBranchCode
chosen
Indicates that an entity is associated with an officer whose organizational or departmental branch is identified by a specific code.
-
B.
denominationBranch
Indicates that one religious organization or group is a subordinate branch, division, or subset of a larger religious denomination.
-
C.
awardingBranch
Indicates the organizational unit or branch that confers or grants an award in the described relationship.
-
D.
operatedBranch
Indicates that one entity functions as a branch location that is run or managed by another entity.
-
E.
hasBranchOffice
Indicates that one organization maintains a branch office or subsidiary location in another place or entity.
- 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_69c69f3567008190ab01d2ca7b53584a |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f9d9c55c8190841f3bf3225c096a |
completed | March 27, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e2e42c8190afc802c4796c9cc2 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:54 p.m.