Triple
T30220731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sasanian Persian forces |
E768336
|
entity |
| Predicate | usedPrimaryArm |
P78511
|
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: [Sasanian Persian forces, usedPrimaryArm, heavy cavalry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedPrimaryArm Context triple: [Sasanian Persian forces, usedPrimaryArm, heavy cavalry]
-
A.
primaryArms
chosen
Indicates that the subject possesses or uses the specified arms or weapons as its main or most important set.
-
B.
usedInPrimary
Indicates that something serves as the main or principal context, setting, or application in which another thing is used.
-
C.
hasArm
Indicates that one entity possesses or is equipped with an arm as a physical part or component of itself.
-
D.
isPrimarilyUsedAs
Indicates that one entity serves mainly or most commonly in the role, function, or purpose specified by the other entity.
-
E.
laterArm
Indicates that one event, state, or action occurs at a later time than another within the same arm or branch of a process or study.
- 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_69f2247fd8b8819087fcf83cb7a05eb8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a16debc8190a12f5f65ced055d7 |
completed | May 2, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f6860def1c81909d79e1f088c4b5e5 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 7:35 p.m.