Triple
T4558905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman magistracy |
E120545
|
entity |
| Predicate | imposesRule |
P7925
|
FINISHED |
| Object | one-year term for most offices |
—
|
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: one-year term for most offices | Statement: [Roman magistracy, imposesRule, one-year term for most offices]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imposesRule Context triple: [Roman magistracy, imposesRule, one-year term for most offices]
-
A.
imposes
chosen
Indicates that one entity enforces, applies, or places a rule, condition, burden, or obligation upon another entity.
-
B.
setsRulesFor
Indicates that one entity establishes or defines rules, guidelines, or constraints that another entity is expected to follow.
-
C.
usesRulesFrom
Indicates that one entity applies, follows, or is governed by the rules defined or provided by another entity.
-
D.
isRuleGoverned
Indicates that an entity’s behavior, structure, or operation is determined and constrained by explicit rules or formal regulations.
-
E.
imposedOn
Indicates that one party enforces, applies, or places a requirement, burden, or constraint onto another party or entity.
- 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_69bd4636f1648190a701445c2fcd9c17 |
completed | March 20, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69bd5829cc34819086ad2ae58446502e |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd52254c648190a5144cfe8fa7e409 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.