Triple
T21474418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Crowell |
E529816
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Andrew Crowell |
—
|
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 Crowell | Statement: [Andrew Crowell, name, Andrew Crowell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Crowell Context triple: [Andrew Crowell, name, Andrew Crowell]
-
A.
Andrew Crowell
chosen
Andrew Crowell is an individual notable enough to be specifically referenced as a bearer of the Crowell surname.
-
B.
Colin Kroll
Colin Kroll was an American technology entrepreneur best known as the co-founder of the short-form video platform Vine and the mobile trivia game HQ Trivia.
-
C.
Jason Crouse
Jason Crouse is a fictional defense investigator and love interest of Alicia Florrick on the legal drama television series "The Good Wife."
-
D.
Michael Andrews
Michael Andrews is an American film composer and musician known for his atmospheric scores for movies such as Donnie Darko and Bridesmaids.
-
E.
Michael Andrews
Michael Andrews was a prominent British painter associated with the School of London, known for his psychologically charged figurative works and atmospheric landscapes.
- 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_69e0c459acb481909bb6ee452a0045c7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea1650788190bd55ebdbf1dfc46f |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:19 p.m.