Triple
T5474972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theatre of Dodona |
E122928
|
entity |
| Predicate | modifiedInPeriod |
P56192
|
FINISHED |
| Object | 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: Roman period | Statement: [Theatre of Dodona, modifiedInPeriod, Roman period]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modifiedInPeriod Context triple: [Theatre of Dodona, modifiedInPeriod, Roman period]
-
A.
hasAlterationPeriod
chosen
Indicates that an entity is associated with a specific time span during which changes, modifications, or alterations may occur or are valid.
-
B.
updatedIn
Indicates that an entity has undergone a change or modification within a specified time period or version context.
-
C.
canBeModifiedBetween
Indicates that something is allowed or able to be changed during a specified interval or between defined points or states.
-
D.
laterModifiedTo
Indicates that an entity was changed or updated at a later time into another specified form or state.
-
E.
hasHumanModification
Indicates that an entity has been altered, influenced, or modified as a result of human activity or intervention.
- 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_69bd46459ff48190823377457bcf7128 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd923465c88190ad9c1b75b268f7ca |
completed | March 20, 2026, 6:30 p.m. |
| PD | Predicate disambiguation | batch_69bd91a58c448190904964a439045e05 |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:09 p.m.