Triple
T22274407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Assassins |
E550563
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Steve Kahan |
—
|
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: Steve Kahan | Statement: [Assassins, starring, Steve Kahan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steve Kahan Context triple: [Assassins, starring, Steve Kahan]
-
A.
Steve Kahan
chosen
Steve Kahan is an American character actor best known for his supporting roles in action and thriller films, particularly frequent collaborations with director Richard Donner.
-
B.
Ken Koblun
Ken Koblun is a Canadian bassist best known for his early involvement with the influential 1960s rock band Buffalo Springfield.
-
C.
Steve Kirsch
Steve Kirsch is an American entrepreneur and inventor best known for founding multiple technology companies, including the early internet search engine Infoseek.
-
D.
Eric Lofgren
Eric Lofgren is an epidemiologist known for using World of Warcraft’s Corrupted Blood incident as a model to study the spread of infectious diseases and human behavior during epidemics.
-
E.
Michael Krieger
Michael Krieger is a fictional character appearing in the story of "Watch Over Me."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e43d8208190aff4f9cf7f2c2a8a |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14ea643d48190985371d01aac7bfc |
completed | April 29, 2026, 12:19 a.m. |
Created at: April 16, 2026, 8:40 p.m.