Triple
T22167831
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Ott's Sneeze |
E547841
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Fred Ott |
—
|
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: Fred Ott | Statement: [Fred Ott's Sneeze, stars, Fred Ott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fred Ott Context triple: [Fred Ott's Sneeze, stars, Fred Ott]
-
A.
Fred Ott
chosen
Fred Ott was a Thomas Edison employee best known as the subject of one of the earliest motion pictures, "Fred Ott's Sneeze."
-
B.
James Dooley
James Dooley is a composer best known for creating dramatic, cinematic music often used in film, television, and trailer scores.
-
C.
Frank Lackteen
Frank Lackteen was a Lebanese-born American character actor best known for playing sinister or exotic villains in numerous silent and early sound film serials and Westerns.
-
D.
Marshall Flinkman
Marshall Flinkman is a quirky, brilliant tech expert and gadget inventor from the television series "Alias," known for providing high-tech support to the show's spies.
-
E.
Frank Frink
Frank Frink is a central character in Philip K. Dick's alternate-history novel "The Man in the High Castle," portrayed as a disillusioned craftsman navigating life under Axis-occupied America.
- 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_69e11e3c4c5c81908d336165816b12e0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12a6642b08190980fa0c0d2bb4229 |
completed | April 28, 2026, 9:45 p.m. |
Created at: April 16, 2026, 8:34 p.m.