Triple
T23182088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elvis and Me |
E579489
|
entity |
| Predicate | coAuthor |
P398
|
FINISHED |
| Object | Sandra Harmon |
E581204
|
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: Sandra Harmon | Statement: [Elvis and Me, coAuthor, Sandra Harmon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandra Harmon Context triple: [Elvis and Me, coAuthor, Sandra Harmon]
-
A.
Sandra Harmon
chosen
Sandra Harmon is an American writer and collaborator known for co-authoring books with high-profile figures, including Priscilla Presley.
-
B.
Sandra Davenport
Sandra Davenport is the first wife of American actor and comedian Jim Belushi, with whom she has one son.
-
C.
Darlene Gillespie
Darlene Gillespie is an American singer and former child actress best known as one of the original Mouseketeers on the 1950s television show The Mickey Mouse Club.
-
D.
Angie Hicks
Angie Hicks is an American entrepreneur best known as the co-founder and namesake of Angi (formerly Angie’s List), a popular online marketplace for home services and contractor reviews.
-
E.
Sandra Coney
Sandra Coney is a New Zealand feminist, writer, and women's health advocate known for her activism, journalism, and work in public health and local government.
- 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f6f770c81908622085693e37123 |
completed | April 29, 2026, 4:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c30b3e07481908a4867997cbc5588 |
completed | May 19, 2026, 9:43 a.m. |
Created at: April 17, 2026, 4:05 p.m.