Triple
T5146509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bob Jones University |
E116082
|
entity |
| Predicate | issuedApology |
P56122
|
FINISHED |
| Object | apologized in 2008 for past racial policies |
—
|
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: apologized in 2008 for past racial policies | Statement: [Bob Jones University, issuedApology, apologized in 2008 for past racial policies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: issuedApology Context triple: [Bob Jones University, issuedApology, apologized in 2008 for past racial policies]
-
A.
apologyIssued
Indicates that one entity has expressed regret or remorse to another entity for a perceived wrong, mistake, or offense.
-
B.
apologyIssuedBy
chosen
Indicates that an apology has been made by a specific entity as the source or initiator of that apology.
-
C.
apologizedFor
Indicates that one entity expressed regret or remorse to another entity specifically about a particular action, event, or wrongdoing.
-
D.
typeOfApology
Indicates that one entity specifies the particular kind or category of apology expressed in relation to another entity.
-
E.
apologyDate
Indicates the date on which an apology was made or formally recorded.
- 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_69bd4446c0e08190a7c29dc74976bf03 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd78d7f4d081908d59adcd86f52f1d |
completed | March 20, 2026, 4:42 p.m. |
| PD | Predicate disambiguation | batch_69bd77ae2f10819098bb8939106e1281 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:43 p.m.