Triple
T33181211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diane Sterling |
E849332
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | NCIS character |
C57359
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: NCIS character Context triple: [Diane Sterling, instanceOf, NCIS character]
-
A.
NCIS character
chosen
An NCIS character is a fictional individual who works within or interacts closely with the Naval Criminal Investigative Service, contributing to the investigation and resolution of crimes involving the U.S. Navy and Marine Corps.
-
B.
NCIS agent
An NCIS agent is a federal law enforcement officer responsible for investigating crimes involving the U.S. Navy and Marine Corps, including criminal, counterintelligence, and counterterrorism matters.
-
C.
NCIS special agent
An NCIS special agent is a federal law enforcement officer responsible for investigating crimes involving the U.S. Navy and Marine Corps, including criminal, counterintelligence, and counterterrorism matters.
-
D.
S.H.I.E.L.D. agent
A S.H.I.E.L.D. agent is a highly trained operative working for the Strategic Homeland Intervention, Enforcement and Logistics Division, specializing in intelligence gathering, covert operations, and defense against extraordinary threats.
-
E.
Tom Clancy character
A Tom Clancy character is a highly trained, often morally complex operative, analyst, or leader navigating realistic military, intelligence, and geopolitical conflicts with a focus on technical detail and strategic decision-making.
- F. None of above.
Provenance (1 batch)
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_69f3495d06508190b0b7729982982cea |
completed | April 30, 2026, 12:21 p.m. |
Created at: May 1, 2026, 1:29 a.m.