Triple
T19850616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andy Cohen |
E476982
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Andrew Joseph Cohen |
—
|
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: Andrew Joseph Cohen | Statement: [Andy Cohen, fullName, Andrew Joseph Cohen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Joseph Cohen Context triple: [Andy Cohen, fullName, Andrew Joseph Cohen]
-
A.
Andrew Cohen
Andrew Cohen is a film editor known for his work on the action thriller "Deadly Impact."
-
B.
Andrew Cohen
Andrew Cohen is an entrepreneur best known as a founder of the wireless technology company Qualcomm.
-
C.
Andrew Cohen
Andrew Cohen is a theoretical physicist known for his work in particle physics and for being one of Howard Georgi’s prominent students.
-
D.
Andrew Cohen
chosen
Andrew Cohen is an American television producer and media executive best known for creating and hosting Bravo’s late-night talk show "Watch What Happens Live with Andy Cohen."
-
E.
Andrew J. Cohen
Andrew J. Cohen is an American screenwriter and director best known for co-writing hit comedy films such as Neighbors and its sequel.
- 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65867b5408190bbd12ca567c4705f |
completed | April 20, 2026, 4:46 p.m. |
Created at: April 10, 2026, 1:51 p.m.