Triple
T20930035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maratha region |
E515445
|
entity |
| Predicate | traditionalMilitaryRole |
P9463
|
FINISHED |
| Object | cavalry |
—
|
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: cavalry | Statement: [Maratha region, traditionalMilitaryRole, cavalry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalMilitaryRole Context triple: [Maratha region, traditionalMilitaryRole, cavalry]
-
A.
militaryRole
chosen
Indicates the specific function, position, or duty an entity holds within a military organization or context.
-
B.
formerMilitaryRole
Indicates that an entity previously held, but no longer holds, a specific military role or position.
-
C.
favoredMilitaryRole
Indicates the military position, function, or specialization that an entity prefers or is most inclined to choose.
-
D.
civilOrMilitary
Indicates that something is classified as either civil (non-military) or military in nature or function.
-
E.
militaryResponsibility
Indicates that an entity holds authority, duty, or accountability for military actions, operations, or forces in relation to 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f6545f8c81908a8c2f0e8d7b060e |
completed | April 21, 2026, 4 a.m. |
| PD | Predicate disambiguation | batch_69e5c9af1fe08190953366a466950140 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:49 p.m.