Triple
T7259552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warren Oates |
E159612
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Vickery Oates |
E159612
|
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: Vickery Oates | Statement: [Warren Oates, spouse, Vickery Oates]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vickery Oates Context triple: [Warren Oates, spouse, Vickery Oates]
-
A.
Vickery Oates
chosen
Vickery Oates is best known as the wife of American character actor Warren Oates.
-
B.
Jean Purdy
Jean Purdy was a British nurse and embryologist who played a pivotal role in developing in vitro fertilization, helping to create the world’s first “test-tube baby.”
-
C.
O’Neil Ford
O’Neil Ford was a prominent 20th-century American architect known for his modernist designs that integrated regional materials and traditions, particularly in Texas.
-
D.
Rachel Owen
Rachel Owen was a Welsh artist, printmaker, and academic known for her work inspired by Dante’s "Divine Comedy" and for her long-term relationship with Radiohead frontman Thom Yorke.
-
E.
Mel Sharples
Mel Sharples is a gruff but good-hearted diner owner and cook from the sitcom "Alice," known for his no-nonsense attitude and catchphrase, "Stow it!"
- 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_69c68838f9948190875fd60b2351230c |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eac5311c819094fc6880f3152813 |
completed | March 27, 2026, 8:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7e5269d1c8190a56624530f9af48b |
completed | March 28, 2026, 2:26 p.m. |
Created at: March 27, 2026, 2:57 p.m.