Triple
T2800413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Monica Lewinsky scandal |
E53139
|
entity |
| Predicate | relatedInvestigation |
P6157
|
FINISHED |
| Object | Ken Starr investigation |
—
|
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: Ken Starr investigation | Statement: [Monica Lewinsky scandal, relatedInvestigation, Ken Starr investigation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedInvestigation Context triple: [Monica Lewinsky scandal, relatedInvestigation, Ken Starr investigation]
-
A.
investigatedFor
Indicates that an entity is the subject of an investigation concerning a suspected involvement in another entity (typically a crime, incident, or wrongdoing).
-
B.
investigatedBy
chosen
Indicates that an entity is the subject of an investigation carried out by another entity.
-
C.
relatedTest
Indicates that there exists some form of connection or association between one test and another.
-
D.
relatedMIC
Indicates that there exists a relationship or connection between entities involving a MIC (Minimum Inhibitory Concentration) context, such as shared, comparable, or associated MIC values or measurements.
-
E.
relatedCase
Indicates that one legal case is connected or associated with another case, such as through shared facts, parties, issues, or procedural history.
- 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_69ab495a90788190941b6917e1eca3a6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abde2ec2ac8190bd702ad3eafb6aed |
completed | March 7, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69abdd059f308190853191f6ffe2bc6f |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:58 p.m.