Triple
T9200312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarmatians |
E220819
|
entity |
| Predicate | warfareSpecialization |
P709
|
FINISHED |
| Object | heavy 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: heavy cavalry | Statement: [Sarmatians, warfareSpecialization, heavy cavalry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: warfareSpecialization Context triple: [Sarmatians, warfareSpecialization, heavy cavalry]
-
A.
warfareCapability
Indicates the ability or capacity of an entity to engage in, conduct, or support acts of warfare.
-
B.
warfareType
Indicates the specific kind or category of warfare that characterizes a given conflict or military engagement.
-
C.
usedWarfareType
chosen
Indicates the specific type or method of warfare that an entity employed in a conflict or military context.
-
D.
militaryCharacteristic
Indicates that one entity possesses a specific military-related attribute, quality, or feature in relation to another entity or context.
-
E.
militaryDomain
Indicates that the relationship or action occurs within, pertains to, or is specifically associated with the military sphere or context.
- 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_69ca83e8e9248190862cf3e41693b310 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccd881c5d48190bbc33fac71a1d849 |
completed | April 1, 2026, 8:34 a.m. |
| PD | Predicate disambiguation | batch_69cc660af2408190ae06eb8326e1c64e |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:25 p.m.