Triple
T16329986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | General Sternwood |
E396524
|
entity |
| Predicate | hiresFor |
P59576
|
FINISHED |
| Object | investigating blackmail involving Carmen Sternwood |
—
|
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: investigating blackmail involving Carmen Sternwood | Statement: [General Sternwood, hiresFor, investigating blackmail involving Carmen Sternwood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hiresFor Context triple: [General Sternwood, hiresFor, investigating blackmail involving Carmen Sternwood]
-
A.
hires
chosen
Indicates that one entity employs or contracts another entity to perform work or services.
-
B.
canHire
Indicates that one entity has the authority or ability to employ or recruit another entity.
-
C.
workFor
Indicates that one entity is employed by or performs work under the authority or direction of another entity.
-
D.
holdsWorkBy
Indicates that one entity possesses, contains, or displays a work that was created by another entity.
-
E.
commissionedFor
Indicates that something was formally requested or created to serve a specific purpose, project, or recipient.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4debef08190a64f13214bfa098f |
completed | April 17, 2026, 11:40 p.m. |
| PD | Predicate disambiguation | batch_69e226eba9b48190af6e80d3d1c2aed3 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.