Triple
T18308102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Cynoscephalae |
E438542
|
entity |
| Predicate | militaryFormationUsedByRomans |
P15598
|
FINISHED |
| Object | manipular 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: manipular legion | Statement: [Battle of Cynoscephalae, militaryFormationUsedByRomans, manipular legion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryFormationUsedByRomans Context triple: [Battle of Cynoscephalae, militaryFormationUsedByRomans, manipular legion]
-
A.
usedMilitaryFormation
chosen
Indicates that an entity employed a specific military formation or tactical arrangement of forces in a military context.
-
B.
militaryFormationOf
Indicates that one entity is a military unit or formation that is organizationally part of, or derived from, another entity.
-
C.
RomanArmyType
Indicates the specific organizational or functional category to which a Roman military force belongs (e.g., legion, auxiliary, navy).
-
D.
RomanLegionsPresent
Indicates that Roman military legions are present at or within the specified location or context.
-
E.
militaryFormationLevel
Indicates the hierarchical level or scale of a military formation within an armed forces organizational structure.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50215e0c48190a4679d432b6ee596 |
completed | April 19, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e44fdf43d08190bbcfb6b1fe3cc0ee |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:35 a.m.