Triple
T3392080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Military Justice Reporter |
E71442
|
entity |
| Predicate | coversSubjectArea |
P18525
|
FINISHED |
| Object | military law |
—
|
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: military law | Statement: [Military Justice Reporter, coversSubjectArea, military law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coversSubjectArea Context triple: [Military Justice Reporter, coversSubjectArea, military law]
-
A.
coversField
Indicates that one entity extends over, protects, or occupies the surface or area of a field associated with another entity.
-
B.
coversPolicyArea
Indicates that a policy, document, or initiative includes or addresses a particular policy area or topic within its scope.
-
C.
coversSection
Indicates that one entity includes, addresses, or provides content for a particular section of another entity.
-
D.
subjectMatterScope
chosen
Indicates the thematic or topical domain that an action, statement, or resource pertains to or falls within.
-
E.
usesResearchSubject
Indicates that one entity employs or utilizes another entity as a research subject in a study or investigation.
- 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_69ad85a9c4a88190a854019341cb3b60 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb850594c81909b6f8a384fc98cb2 |
completed | March 8, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69adadf705608190975423779430cc58 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:14 p.m.