Triple
T3386617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aquincum |
E71316
|
entity |
| Predicate | timeOfAbandonment |
P35787
|
FINISHED |
| Object | late 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: late Roman period | Statement: [Aquincum, timeOfAbandonment, late Roman period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeOfAbandonment Context triple: [Aquincum, timeOfAbandonment, late Roman period]
-
A.
stoppedAt
Indicates that an entity has come to a halt or pause at a specific location or point in time.
-
B.
timeAfterAble
Indicates that one event, state, or action occurs after another point in time at which it becomes possible or permissible.
-
C.
timeBetweenAnnouncementAndTermination
Indicates the duration of time that elapses between when something is officially announced and when it is subsequently terminated.
-
D.
endTimeApproximate
chosen
Indicates that the recorded end time of an event or action is not exact but an approximate value.
-
E.
timeToComplete
Indicates the duration required for an entity or process to be fully completed.
- 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_69ad85a8fd9c819095ecedf838d2bf1b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb662d190819085b211dac85a83b2 |
completed | March 8, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69ada43615f08190ac2275020d157983 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:14 p.m.