Triple
T3868482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Timothy Shriver |
E91918
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Shriver |
E93348
|
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: Shriver | Statement: [Timothy Shriver, familyName, Shriver]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shriver Context triple: [Timothy Shriver, familyName, Shriver]
-
A.
Shriver
chosen
Shriver is a prominent American family name associated with notable figures in politics, public service, and media.
-
B.
McClurg
McClurg is the namesake of the historic McClurg Building, a notable structure recognized for its architectural and cultural significance.
-
C.
Corwin
Corwin is a surname most notably associated with Jonathan Corwin, a judge involved in the Salem witch trials in 17th-century Massachusetts.
-
D.
Shaughnessy
Shaughnessy is an affluent residential neighbourhood in Vancouver, British Columbia, known for its large heritage homes and tree-lined streets.
-
E.
Karlin
Karlin is the professional stage name used by Danish songwriter and producer Kenneth Karlin, known for his work in pop and R&B music.
- 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_69aed9645f348190a9868e7cef56ab7e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec3dfb3c8190a0a07070f0d76bf6 |
completed | March 9, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b512440b8c8190ae2048bfcdd565ec |
completed | March 14, 2026, 7:46 a.m. |
Created at: March 9, 2026, 3:20 p.m.