Triple
T28037337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Millman |
E708444
|
entity |
| Predicate | roleInWhenTheWhistleBlows |
P195385
|
FINISHED |
| Object | sitcom star |
—
|
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: sitcom star | Statement: [Andy Millman, roleInWhenTheWhistleBlows, sitcom star]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInWhenTheWhistleBlows Context triple: [Andy Millman, roleInWhenTheWhistleBlows, sitcom star]
-
A.
roleInWhistleblowerCases
Indicates that an entity has a specific role or involvement in one or more whistleblower cases.
-
B.
whistleblowerTerm
Indicates that an entity is designated or treated as a whistleblower, typically one who reports wrongdoing or misconduct within an organization.
-
C.
whistleblowerComplaint
Indicates that an individual has formally reported suspected wrongdoing, misconduct, or illegal activity within an organization to an authority or oversight body.
-
D.
notableWhistleblower
Indicates that the subject is recognized for having exposed significant wrongdoing or misconduct, typically within an organization or institution.
-
E.
roleWhen
Indicates a temporal relationship specifying the time or condition under which a particular role is held or applies.
- F. None of above. chosen
Provenance (4 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
| PDg | Predicate description generation | batch_69fdd07724f88190a33ec602642d2ea3 |
completed | May 8, 2026, noon |
Created at: April 27, 2026, 8:22 p.m.