Triple
T31079292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romana composed circa 551 |
E792056
|
entity |
| Predicate | describesPeriodFrom |
P70694
|
FINISHED |
| Object | legendary origins of Rome |
—
|
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: legendary origins of Rome | Statement: [Romana composed circa 551, describesPeriodFrom, legendary origins of Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: describesPeriodFrom Context triple: [Romana composed circa 551, describesPeriodFrom, legendary origins of Rome]
-
A.
refersToPeriod
Indicates that one entity designates, references, or is associated with a specific time period or interval.
-
B.
chroniclesPeriodFrom
Indicates that something documents or records events starting from a specified point in time or historical period.
-
C.
usePeriodStart
Indicates that an entity begins to be used or becomes active starting from a specified time period.
-
D.
narratedPeriodStart
chosen
Indicates the point in time at which the narrated or described period begins.
-
E.
timePeriodOrigin
Indicates that one entity is the time period in which the other entity originated or first came into existence.
- 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_69f224ccdbbc81909b0cdb4cc2d70c7a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
Created at: April 29, 2026, 9:02 p.m.