Triple
T30220777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sasanian Persian forces |
E768336
|
entity |
| Predicate | hadEliteUnit |
P37488
|
FINISHED |
| Object |
asvaran cavalry
The asvaran cavalry were the elite, heavily armored mounted warriors of the Sasanian Empire, renowned for their decisive role in Persian military power and battlefield tactics.
|
E1905184
|
NE FINISHED |
How this triple was built (3 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: asvaran cavalry | Statement: [Sasanian Persian forces, hadEliteUnit, asvaran cavalry]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: asvaran cavalry Triple: [Sasanian Persian forces, hadEliteUnit, asvaran cavalry]
Generated description
The asvaran cavalry were the elite, heavily armored mounted warriors of the Sasanian Empire, renowned for their decisive role in Persian military power and battlefield tactics.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadEliteUnit Context triple: [Sasanian Persian forces, hadEliteUnit, asvaran cavalry]
-
A.
isEliteUnit
chosen
Indicates that the unit belongs to a specially trained, highly capable subgroup distinguished from regular units.
-
B.
hasSpecialUnit
Indicates that an entity possesses or is associated with a distinct, designated unit that has a special role, function, or status.
-
C.
hasNoble
Indicates that one entity possesses or is associated with a noble title, status, or noble individual.
-
D.
hadFort
Indicates that an entity possessed, controlled, or contained a fort at some time.
-
E.
hadArmiesThat
Indicates that an entity possessed, controlled, or was associated with one or more armies.
- F. None of above.
Provenance (6 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_69f6801da3e88190a4862f59160e6832 |
completed | May 2, 2026, 10:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a27643d4b8c81908cae65b88f089b37 |
completed | June 9, 2026, 12:54 a.m. |
| NEDg | Description generation | batch_6a2764f2c6588190b88039903b3d891c |
completed | June 9, 2026, 12:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a2766191bf48190bc484ef33593dc28 |
completed | June 9, 2026, 1:02 a.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:35 p.m.