Triple
T35270752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Medal of Honor |
E1018659
|
entity |
| Predicate | laterBranchAuthorized |
P202190
|
FINISHED |
| Object | United States Air Force |
—
|
NE NERFINISHED |
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: United States Air Force | Statement: [Medal of Honor, laterBranchAuthorized, United States Air Force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterBranchAuthorized Context triple: [Medal of Honor, laterBranchAuthorized, United States Air Force]
-
A.
legitimizedBranch
Indicates that one entity has granted official recognition or legal validity to a subordinate or derivative branch of another entity.
-
B.
laterApprovedFor
Indicates that one entity was granted approval for another entity at a subsequent time after an earlier point or event.
-
C.
laterPermittedBy
Indicates that an action or state becomes allowed at a later time due to a specific permission, rule, or authority.
-
D.
previouslyAuthorizedBy
Indicates that an action, access, or decision was granted or approved earlier by a specified entity or authority.
-
E.
trainedBranch
Indicates that one entity has provided training or instruction to a specific branch or subdivision of another entity.
- F. None of above. chosen
Provenance (4 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_69f76de5c4788190896ad598ae7d6bc6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a005e8a2f7c819085bfc6f04b866d87 |
completed | May 10, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_6a005de82ef08190a015b385d1d3443c |
completed | May 10, 2026, 10:28 a.m. |
| PDg | Predicate description generation | batch_6a005e89803c8190ad732ad15affb81f |
completed | May 10, 2026, 10:31 a.m. |
Created at: May 3, 2026, 4:02 p.m.