Triple
T32300657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nova Roma |
E825228
|
entity |
| Predicate | refoundedFrom |
P109904
|
FINISHED |
| Object | Byzantium |
—
|
NE NERFINISHED |
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: Byzantium | Statement: [Nova Roma, refoundedFrom, Byzantium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refoundedFrom Context triple: [Nova Roma, refoundedFrom, Byzantium]
-
A.
refoundedBy
Indicates that an entity was re-established or reconstituted by another entity after a period of inactivity, dissolution, or significant change.
-
B.
laterRefoundedAs
chosen
Indicates that an entity was dissolved or ceased to exist and was subsequently re-established under a new or modified form, identity, or organization.
-
C.
reforgedFrom
Indicates that something has been newly created or remade by reshaping or reworking a previous object or material.
-
D.
foundedFrom
Indicates that an entity was established or originated starting from a particular source, place, or prior entity.
-
E.
reconfiguredFrom
Indicates that one entity has been altered, adapted, or rearranged from a prior entity or configuration, such that the current form results from modifying the original.
- 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_69f349115304819084ee91d345b6c8aa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bd7481988190addeb1c9acd75386 |
completed | May 3, 2026, 3:13 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:45 a.m.