Triple
T10269109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vannius |
E240787
|
entity |
| Predicate | politicalRelationToRome |
P47199
|
FINISHED |
| Object | client relationship |
—
|
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: client relationship | Statement: [Vannius, politicalRelationToRome, client relationship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalRelationToRome Context triple: [Vannius, politicalRelationToRome, client relationship]
-
A.
laterRelationToRome
Indicates that one entity occurs or exists at a time later than the reference time associated with Rome.
-
B.
politicalRelation
chosen
Indicates a relationship between entities that involves political alignment, influence, affiliation, conflict, or cooperation within a political context.
-
C.
consideredByRomeAs
Indicates that something or someone is regarded or classified in a particular way by Rome (e.g., Roman authorities, culture, or legal system).
-
D.
romanProvinceRelation
Indicates a relationship where one entity functioned as, or was part of, a Roman province administered by another entity.
-
E.
cededToPapalStatesBy
Indicates that control or sovereignty over an entity was transferred to the Papal States by another 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_69d381a94c1881908fc38fc263d9b9c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2872830819080fdfa816167d04c |
completed | April 7, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69d4d1ef6e6c81908a8ee52e4d28127b |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:35 a.m.