Triple
T7769103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ralph Carter |
E179024
|
entity |
| Predicate | characterRole |
P268
|
FINISHED |
| Object | Michael Evans |
E213900
|
NE FINISHED |
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: Michael Evans | Statement: [Ralph Carter, characterRole, Michael Evans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Evans Context triple: [Ralph Carter, characterRole, Michael Evans]
-
A.
Michael Evans
chosen
Michael Evans is a smart, socially conscious teenage son in the 1970s sitcom "Good Times," often serving as the show's outspoken voice on political and racial issues.
-
B.
Jack Evans
Jack Evans is an actor known for appearing in the film "Hellgate."
-
C.
Michael Lynn Evans III
Michael Lynn Evans III is an American professional football wide receiver best known for his standout career with the Tampa Bay Buccaneers in the NFL.
-
D.
James Evans
James Evans was a 19th-century British-Canadian missionary and linguist best known for developing the syllabic writing system used by several Indigenous languages in Canada.
-
E.
Jonathan Evans
Jonathan Evans is a British politician and former Member of Parliament who has served in both the UK and European Parliaments.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c69f30602c819082ab52cd4af5c592 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c704376dc08190890f5ebb9f259cfd |
completed | March 27, 2026, 10:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8deb127048190a89c08b7778df8a4 |
completed | March 29, 2026, 8:11 a.m. |
Created at: March 27, 2026, 4:11 p.m.