Triple
T37358704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masetto |
E927521
|
entity |
| Predicate | suspectsInfidelityOf |
P91911
|
FINISHED |
| Object | Zerlina |
—
|
NE NERFINISHED |
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: Zerlina | Statement: [Masetto, suspectsInfidelityOf, Zerlina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectsInfidelityOf Context triple: [Masetto, suspectsInfidelityOf, Zerlina]
-
A.
isLedToBelieveWifeUnfaithfulWith
Indicates that one person is caused or persuaded to believe that their wife is being unfaithful with another specified person.
-
B.
wasCheatedOnBy
Indicates that one entity was the victim of infidelity committed by another entity in a romantic or committed relationship.
-
C.
hasAffairWith
Indicates that one entity is engaged in a secret or illicit romantic or sexual relationship with another entity, typically outside a committed partnership.
-
D.
hasMultipleSuspectsInPlot
Indicates that a plot or scheme involves more than one individual as suspects.
-
E.
isSuspiciousOf
chosen
Indicates that one entity believes another entity or situation may be untrustworthy, harmful, or involved in wrongdoing.
- 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_69f76eb701788190b40824bc4594d985 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.