Triple
T1143778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batavi |
E23515
|
entity |
| Predicate | roleInRomanArmy |
P9463
|
FINISHED |
| Object | bodyguard cavalry for Roman emperors |
—
|
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: bodyguard cavalry for Roman emperors | Statement: [Batavi, roleInRomanArmy, bodyguard cavalry for Roman emperors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInRomanArmy Context triple: [Batavi, roleInRomanArmy, bodyguard cavalry for Roman emperors]
-
A.
RomanRepresentative
Indicates that one entity serves as an official representative or agent of the Roman state, authority, or interests in relation to another entity.
-
B.
militaryRole
chosen
Indicates the specific function, position, or duty an entity holds within a military organization or context.
-
C.
underRomanRule
Indicates that one entity was politically controlled or governed by the Roman state or its authorities.
-
D.
soldierCaste
Indicates that an entity belongs to, or is characterized as part of, a soldier or warrior class within a social or organizational hierarchy.
-
E.
isRegularArmyUnit
Indicates that the entity functions as a formal, organized military unit within a country's regular (non-irregular) armed forces.
- 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_69a493ef399c8190b04b9146d2314f59 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc5008d8819095c1ffb5db5b4911 |
completed | March 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4d4104819084027a043c6118cb |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.