Triple
T447640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maratha Empire |
E7055
|
entity |
| Predicate | militaryStrength |
P11878
|
FINISHED |
| Object | cavalry-based warfare |
—
|
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-based warfare | Statement: [Maratha Empire, militaryStrength, cavalry-based warfare]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryStrength Context triple: [Maratha Empire, militaryStrength, cavalry-based warfare]
-
A.
warPower
Indicates the authority, capability, or legal power to initiate, conduct, or manage acts of war or armed conflict.
-
B.
warTimeStrengthApprox
chosen
Indicates an approximate measure of an entity’s military strength or capacity during a time of war.
-
C.
combatantStrength
Indicates the relative level of power, capability, or effectiveness one combatant has in a conflict or confrontation compared to others.
-
D.
warfareCapability
Indicates the ability or capacity of an entity to engage in, conduct, or support acts of warfare.
-
E.
militaryMeasure
Indicates a relationship where an entity undertakes, imposes, or is subject to a specific military-related action, policy, or operational measure.
- 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_69a2e7e4676c81909ea0dbdecac0687c |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ef6429e881908aa758da64299a16 |
completed | Feb. 28, 2026, 1:36 p.m. |
| PD | Predicate disambiguation | batch_69a2eddfb5508190a4e06e1b260d8b2b |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.