Triple
T285015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman legion |
E5868
|
entity |
| Predicate | hasLaterRecruitmentBase |
P5414
|
FINISHED |
| Object | all male Roman citizens |
—
|
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: all male Roman citizens | Statement: [Roman legion, hasLaterRecruitmentBase, all male Roman citizens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLaterRecruitmentBase Context triple: [Roman legion, hasLaterRecruitmentBase, all male Roman citizens]
-
A.
introducedAfter
Indicates that one entity was introduced at a later time or stage than another entity.
-
B.
hasCadetBranch
Indicates that one lineage, family, or house is a junior or offshoot branch derived from another main or senior line.
-
C.
usesConscription
Indicates that a state or authority compels individuals into military or national service through mandatory conscription.
-
D.
recruitmentBase
Indicates the foundational source, location, or context from which recruitment efforts or recruited entities originate.
-
E.
recruitmentBasis
chosen
Indicates the criteria, grounds, or conditions on which an entity is recruited or selected for a role or position.
- 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.