Triple
T23548656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Everest |
E577974
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Michael Kelly |
—
|
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: Michael Kelly | Statement: [Everest, castMember, Michael Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Kelly Context triple: [Everest, castMember, Michael Kelly]
-
A.
Michael Kelly
Michael Kelly is an American sports executive best known for serving as the athletic director at the University of South Florida.
-
B.
Michael Kelly
chosen
Michael Kelly is an American actor best known for his role as Doug Stamper on the political drama series "House of Cards."
-
C.
Michael Kelly
Michael Kelly is a film editor best known for his work on the animated feature "The Rescuers Down Under."
-
D.
Michael Kelly
Michael Kelly was an Irish journalist and editor known for his influential work in Irish media, for whom the Michael Kelly Award for journalism is named.
-
E.
Michael Walsh
Michael Walsh is a common personal name shared by numerous individuals across various fields such as politics, sports, literature, and entertainment.
- 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_69e245fa93448190919cb04534560542 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1aecc2af08190aec07cf9126d4e72 |
completed | April 29, 2026, 7:10 a.m. |
Created at: April 17, 2026, 6:11 p.m.