Triple
T21952149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Electric Horseman |
E542094
|
entity |
| Predicate | storyBy |
P1955
|
FINISHED |
| Object | Paul Gaer |
—
|
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: Paul Gaer | Statement: [The Electric Horseman, storyBy, Paul Gaer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Gaer Context triple: [The Electric Horseman, storyBy, Paul Gaer]
-
A.
Paul Gaer
chosen
Paul Gaer was a screenwriter best known for his work on the 1979 film "The Electric Horseman."
-
B.
Paul Graetz
Paul Graetz was a French film producer active in the mid-20th century, known for backing a range of notable European films.
-
C.
Paul Gout
Paul Gout was a French architect and restorer known for his work on medieval monuments and historic structures in France.
-
D.
Paul Vischer
Paul Vischer was a member of the notable Vischer family of German sculptors active during the Renaissance period.
-
E.
Charles Egeler
Charles Egeler was an American prison warden and corrections official in Michigan, best known for his leadership at the State Prison of Southern Michigan.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243c84d4819097f5a93b128f024b |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:58 p.m.