Triple
T21917852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Solarium Augusti |
E541226
|
entity |
| Predicate | typeOfTimekeeping |
P145624
|
FINISHED |
| Object | solar timekeeping |
—
|
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: solar timekeeping | Statement: [Solarium Augusti, typeOfTimekeeping, solar timekeeping]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfTimekeeping Context triple: [Solarium Augusti, typeOfTimekeeping, solar timekeeping]
-
A.
timeType
Indicates the specific temporal category or classification associated with a time-related entity or value (e.g., duration, point in time, interval, or recurrence type).
-
B.
timeStatus
Indicates the temporal state or condition of an event or entity relative to a reference time (e.g., past, present, future, ongoing, or scheduled).
-
C.
propertyType_ptime
Indicates that a property has an associated time-related characteristic or classification (e.g., duration, timestamp, or temporal category).
-
D.
officialTimekeeper
Indicates that one entity serves as the formally designated timekeeper or time-recording authority for another entity or event.
-
E.
timeRecorded
Indicates that a specific point or period in time has been captured and stored as associated with an event, action, or state.
- 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_69e0c47c4b9c8190a5586a75f5f36453 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1233924008190923724d0c0f2d435 |
completed | April 28, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
| PDg | Predicate description generation | batch_69e6c187bc548190b4ca13150f6bae38 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 7:43 p.m.