Triple
T21767005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evil Ed Lee |
E537318
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Stephen Geoffreys |
—
|
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: Stephen Geoffreys | Statement: [Evil Ed Lee, portrayedBy, Stephen Geoffreys]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stephen Geoffreys Context triple: [Evil Ed Lee, portrayedBy, Stephen Geoffreys]
-
A.
Stephen Geoffreys
chosen
Stephen Geoffreys is an American actor best known for his cult-favorite horror and teen film roles of the 1980s.
-
B.
Geoffrey Lawrence
Geoffrey Lawrence was a British judge best known for serving as the presiding judge at the Nuremberg war crimes trials after World War II.
-
C.
Geoffrey Will
Geoffrey Will is the son of prominent American conservative political commentator and columnist George F. Will.
-
D.
Geoffrey Unsworth
Geoffrey Unsworth was a renowned British cinematographer celebrated for his visually rich work on numerous classic films of the 1960s and 1970s.
-
E.
Francis Weir
Francis Weir is an individual notable enough to be recognized as a bearer of the surname Weir, though specific widely known biographical details about them are not well documented.
- 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_69e0c46f5d1c8190bf830409e98464e5 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031aa9c888190887c5c1d1e3bab9f |
completed | April 28, 2026, 4:03 a.m. |
Created at: April 16, 2026, 6:51 p.m.