Triple
T285025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman legion |
E5868
|
entity |
| Predicate | hasPostMarianStructure |
P841
|
FINISHED |
| Object | 10 cohorts per legion |
—
|
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: 10 cohorts per legion | Statement: [Roman legion, hasPostMarianStructure, 10 cohorts per legion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPostMarianStructure Context triple: [Roman legion, hasPostMarianStructure, 10 cohorts per legion]
-
A.
hasIconicStructure
Indicates that an entity possesses a structure or feature that is widely recognized as emblematic or symbolically representative of it.
-
B.
hasStructureType
chosen
Indicates that an entity possesses or is classified by a specific structural type or configuration.
-
C.
hasCommandStructure
Indicates that one entity possesses an organized hierarchy of authority or control that governs another entity or set of entities.
-
D.
hasOrganizationalStructure
Indicates that an entity possesses a defined internal arrangement of roles, responsibilities, and relationships that determine how it is organized and operates.
-
E.
hasLinguisticElement
Indicates that one entity includes, is associated with, or is characterized by a particular linguistic component such as a word, phrase, symbol, or other language element.
- 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_69a25946a7ac8190a78871c210213272 |
completed | Feb. 28, 2026, 2:56 a.m. |
| NER | Named-entity recognition | batch_69a2605b372c8190831570aa6532cc96 |
completed | Feb. 28, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69a25b7a8d148190aacdcc8ccb35c7f3 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 3:02 a.m.