Triple
T34629133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Mauretania |
E889222
|
entity |
| Predicate | wasClientKingdomOf |
P106028
|
FINISHED |
| Object | Roman Empire |
—
|
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: Roman Empire | Statement: [Roman Mauretania, wasClientKingdomOf, Roman Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasClientKingdomOf Context triple: [Roman Mauretania, wasClientKingdomOf, Roman Empire]
-
A.
wasClientKingdomUntil
Indicates that an entity functioned as a client kingdom subordinate to another entity up until a specified end date or time.
-
B.
wasKingdom
Indicates that one entity functioned as the sovereign kingdom or ruling polity of another entity during a particular period.
-
C.
wasKingdomUntil
Indicates that an entity functioned as a kingdom governing another entity up to a specified end time or event.
-
D.
clientKingdomOf
chosen
Indicates a relationship where one kingdom is politically subordinate or tributary to another, more powerful kingdom while retaining limited internal autonomy.
-
E.
overkingdomOf
Indicates that one kingdom holds overarching authority or sovereignty over another kingdom.
- 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_69f349d64a388190a013cfa9bd33fad7 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7234bcaa48190ac970759d34e254a |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72155c48881909bd40b9aa3febd5a |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:04 a.m.