Triple
T30053296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Defense Service Offices |
E763658
|
entity |
| Predicate | typicalProceedings |
P25382
|
FINISHED |
| Object | special courts-martial |
—
|
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: special courts-martial | Statement: [Defense Service Offices, typicalProceedings, special courts-martial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalProceedings Context triple: [Defense Service Offices, typicalProceedings, special courts-martial]
-
A.
typeOfProceedings
chosen
Indicates the specific category or kind of legal or formal process under which an action or case is being conducted.
-
B.
recordsProceedings
Indicates that an entity documents or captures the details of proceedings, such as events, meetings, or legal actions.
-
C.
proceedingsAre
Indicates that certain events, actions, or legal steps constitute or are recognized as formal proceedings.
-
D.
scriptUsedForProceedings
Indicates that a particular writing system or script is used to record, document, or conduct the referenced proceedings.
-
E.
coversProceedings
Indicates that one entity reports on, documents, or provides coverage of a set of proceedings or events involving another 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_69f224716378819087a722e487832b70 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a03433dd64c8190ab620709153b6278 |
completed | May 12, 2026, 3:11 p.m. |
| PD | Predicate disambiguation | batch_6a034107e53881909127bac98cac3429 |
completed | May 12, 2026, 3:02 p.m. |
Created at: April 29, 2026, 6:56 p.m.