Triple
T17876351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buster Baxter |
E446963
|
entity |
| Predicate | friendOf |
P8712
|
FINISHED |
| Object | Sue Ellen Armstrong |
—
|
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: Sue Ellen Armstrong | Statement: [Buster Baxter, friendOf, Sue Ellen Armstrong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sue Ellen Armstrong Context triple: [Buster Baxter, friendOf, Sue Ellen Armstrong]
-
A.
Sue Ellen Armstrong
chosen
Sue Ellen Armstrong is a kind, artistic, and globally aware cat character from the children's animated series "Arthur," known for her love of world cultures and martial arts.
-
B.
Joan Armstrong
Joan Armstrong is a notable individual distinguished enough to be specifically recognized among people sharing the Armstrong surname.
-
C.
Lynnette Armstrong
Lynnette Armstrong is a notable individual recognized for achievements significant enough to be associated with the surname Armstrong.
-
D.
Sue Armstrong
Sue Armstrong is the wife of British actor Alun Armstrong.
-
E.
Sue Naegle
Sue Naegle is an American television executive and producer best known for her tenure as president of HBO Entertainment and for founding the production company Naegle Ink.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa614b48190bdc9e905e9e6d5e0 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.