Triple
T10014751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clark University |
E199459
|
entity |
| Predicate | hasNotableAlumnus |
P51
|
FINISHED |
| Object | Dyan Cannon |
E109231
|
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: Dyan Cannon | Statement: [Clark University, hasNotableAlumnus, Dyan Cannon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dyan Cannon Context triple: [Clark University, hasNotableAlumnus, Dyan Cannon]
-
A.
Dyan Cannon
chosen
Dyan Cannon is an American actress, director, and producer known for her work in film and television since the 1960s, as well as for her high-profile marriage to Cary Grant.
-
B.
Debbie Rowe
Debbie Rowe is an American nurse best known as Michael Jackson’s ex-wife and the mother of two of his children.
-
C.
Stefanie Powers
Stefanie Powers is an American actress best known for her role as Jennifer Hart in the television series "Hart to Hart."
-
D.
Dana Plato
Dana Plato was an American actress best known for playing Kimberly Drummond on the television sitcom "Diff'rent Strokes."
-
E.
Patti Palmer
Patti Palmer was an American singer and entertainer best known as the first wife of comedian and actor Jerry Lewis.
- 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_69ca8315a1a08190ab310f25620f362b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd49b19c8190b429e3533d072648 |
completed | April 2, 2026, 1:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d3172a7d108190895dad463e7e5423 |
completed | April 6, 2026, 2:15 a.m. |
Created at: March 30, 2026, 8:52 p.m.