Triple
T9308066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Augustan 14 regions of Rome |
E223936
|
entity |
| Predicate | appliesToAspect |
P61123
|
FINISHED |
| Object | census |
—
|
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: census | Statement: [Augustan 14 regions of Rome, appliesToAspect, census]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToAspect Context triple: [Augustan 14 regions of Rome, appliesToAspect, census]
-
A.
refersToAspect
Indicates that one entity specifically references or points to a particular aspect, feature, or component of another entity.
-
B.
appliesTo
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
-
C.
appliesToFeature
Indicates that something (such as a rule, constraint, or configuration) is relevant to, or governs, a specific feature.
-
D.
appliesToComponent
Indicates that a rule, condition, or operation is specifically relevant or applicable to a particular component.
-
E.
coversAspect
chosen
Indicates that one entity addresses, includes, or deals with a particular aspect or facet of another entity or topic.
- 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_69ca8424d0f08190831e2e93c6533aeb |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd1daa21188190b1b2e508b0d09dcb |
completed | April 1, 2026, 1:29 p.m. |
| PD | Predicate disambiguation | batch_69cc7a5ef1908190bc5ca166bb895af6 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:37 p.m.