Triple
T1086895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Revised Julian calendar |
E24072
|
entity |
| Predicate | averageYearError |
P24074
|
FINISHED |
| Object | about 2 seconds per year relative to the tropical 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: about 2 seconds per year relative to the tropical year | Statement: [Revised Julian calendar, averageYearError, about 2 seconds per year relative to the tropical year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: averageYearError Context triple: [Revised Julian calendar, averageYearError, about 2 seconds per year relative to the tropical year]
-
A.
hasAverageYearLength
Indicates that one entity has a specified average duration for its year (orbital period), typically measured over time.
-
B.
yearType
Indicates the classification or category assigned to a specific year (e.g., academic, fiscal, calendar, leap).
-
C.
year
Indicates the specific calendar year associated with an entity, event, or fact.
-
D.
annualFrom
Indicates that something recurs or is calculated on a yearly basis starting from a specified point in time.
-
E.
standardizedInYear
Indicates the specific year in which something was formally standardized or adopted as a standard.
- F. None of above. chosen
Provenance (4 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b963161081908a523c8d63871652 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b7407914819092ed933a7316b450 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b8f1097881908932d7eea4331917 |
completed | March 1, 2026, 10:08 p.m. |
Created at: March 1, 2026, 7:42 p.m.