Triple
T5356315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thugga |
E102699
|
entity |
| Predicate | religionPracticedHistorically |
P7641
|
FINISHED |
| Object | Roman polytheism |
—
|
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 polytheism | Statement: [Thugga, religionPracticedHistorically, Roman polytheism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religionPracticedHistorically Context triple: [Thugga, religionPracticedHistorically, Roman polytheism]
-
A.
religionHistoricallyAssociated
chosen
Indicates a historical association between an entity and a particular religion, based on past practice, tradition, or cultural linkage rather than current or official status.
-
B.
dominantReligionLegacy
Indicates that a historically dominant religion has left a lasting influence or heritage on a society, culture, or region.
-
C.
foundedReligion
Indicates that an entity established or originated a particular religion.
-
D.
religionsPresent
Indicates that one or more religions are present, practiced, or represented in relation to a given entity or context.
-
E.
traditionalReligionName
Indicates that an entity has a name specifically associated with a traditional or indigenous religion.
- 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_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd862f0ea48190bec78690ab3bee51 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.