Triple
T26314645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Elgin |
E661930
|
entity |
| Predicate | personalProblem |
P18260
|
FINISHED |
| Object | alcoholism |
—
|
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: alcoholism | Statement: [Frank Elgin, personalProblem, alcoholism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: personalProblem Context triple: [Frank Elgin, personalProblem, alcoholism]
-
A.
concernsProblem
Indicates that something is about, related to, or deals with a particular problem or issue.
-
B.
problems
chosen
Indicates that one entity has issues, difficulties, or complications associated with or caused by another entity.
-
C.
personalServiceFunction
Indicates a relationship where one entity performs a personal or individualized service function for another entity.
-
D.
typicalProblem
Indicates that a situation, issue, or obstacle is representative or characteristic of the usual problems encountered in a given context.
-
E.
inPersonalLifeImplies
Indicates that a condition or fact in a person's private or non-professional life logically leads to, or has consequences for, another situation or fact.
- 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_69ee812e73048190aae587f1d51e5a06 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620debeb48190b7db395fb86cf8d9 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 26, 2026, 10:24 p.m.