Triple
T21531226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercedonius |
E531233
|
entity |
| Predicate | standardYearContext |
P7173
|
FINISHED |
| Object | Roman 355-day common year |
—
|
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: Roman 355-day common year | Statement: [Mercedonius, standardYearContext, Roman 355-day common year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardYearContext Context triple: [Mercedonius, standardYearContext, Roman 355-day common year]
-
A.
standardizedInYear
Indicates the specific year in which something was formally standardized or adopted as a standard.
-
B.
yearType
chosen
Indicates the classification or category assigned to a specific year (e.g., academic, fiscal, calendar, leap).
-
C.
encounteredYear
Indicates the year in which one entity first came into contact with or met another entity.
-
D.
yearOfReference
Indicates the specific year to which a statement, measurement, or data point is intended to apply or be interpreted with reference.
-
E.
supportsYear
Indicates that one entity is compatible with, or provides functionality for, a specified year or range of years.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d08ebf881909574e098404f93fa |
completed | April 26, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:27 p.m.