Triple
T9442726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grumentum |
E227685
|
entity |
| Predicate | timeOfPeak |
P70162
|
FINISHED |
| Object | Imperial Roman period |
—
|
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: Imperial Roman period | Statement: [Grumentum, timeOfPeak, Imperial Roman period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfPeak Context triple: [Grumentum, timeOfPeak, Imperial Roman period]
-
A.
populationPeakPeriod
Indicates the time period during which a population reached its highest recorded level.
-
B.
peakHours
Indicates that an action, event, or condition occurs during the busiest or most heavily trafficked time period.
-
C.
activityPeakPeriod
chosen
Indicates the time period during which an activity reaches its highest level or intensity.
-
D.
operationalPeak
Indicates the highest level or period of performance, capacity, or activity that a system, process, or entity reaches during its operation.
-
E.
circulationPeak
Indicates the highest level or maximum point reached in the circulation of something (such as money, media, or resources) within a given period or system.
- 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_69ca843884488190ad6cbe0153088234 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f300cc88190a793712706295c53 |
completed | April 1, 2026, 8:25 p.m. |
| PD | Predicate disambiguation | batch_69cca5596ffc819097e9c8eefd4ef9b8 |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:50 p.m.