Triple
T22681822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moesia |
E560500
|
entity |
| Predicate | divisionOccurredInCentury |
P9351
|
FINISHED |
| Object | 1st century AD |
—
|
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: 1st century AD | Statement: [Moesia, divisionOccurredInCentury, 1st century AD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: divisionOccurredInCentury Context triple: [Moesia, divisionOccurredInCentury, 1st century AD]
-
A.
separationCentury
chosen
Indicates the century during which the separation or split between the related entities took place.
-
B.
modernDivision
Indicates that one entity is a contemporary or currently recognized administrative or organizational subdivision of another entity.
-
C.
divisionOccurred
Indicates that one entity has been separated into two or more distinct parts or groups through a division event.
-
D.
latestCentury
Indicates that the associated time or event occurs in, or belongs to, the most recent century relative to a given reference point.
-
E.
coveredSinceCentury
Indicates that one entity has been covered, coated, or kept under coverage continuously starting from a specified century.
- 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_69e2454bfd00819099115715a22cb057 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1786113a881908f60285054d7ecfb |
completed | April 29, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69ee62a6245881909506ff502da14137 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:12 p.m.