Triple
T11356593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onesimus |
E268968
|
entity |
| Predicate | locationOfConversion |
P26505
|
FINISHED |
| Object | prison with Paul |
—
|
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: prison with Paul | Statement: [Onesimus, locationOfConversion, prison with Paul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfConversion Context triple: [Onesimus, locationOfConversion, prison with Paul]
-
A.
locationAfterConversion
Indicates the place or position an entity occupies after it has been transformed, converted, or changed from one state or form to another.
-
B.
placeOfConversion
chosen
Indicates the location where an entity undergoes a religious, ideological, or formal conversion.
-
C.
locationOfCampaign
Indicates the place or geographic area where a particular campaign is conducted or based.
-
D.
locationWhenGiven
Indicates the place where an entity is located at the time it is given or transferred to another entity.
-
E.
operationLocation
Indicates the place or site where an operation, activity, or process is carried out.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.