Triple
T9813291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wyatt Tee Walker |
E238331
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Theresa Ann Walker |
E238331
|
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: Theresa Ann Walker | Statement: [Wyatt Tee Walker, spouse, Theresa Ann Walker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Theresa Ann Walker Context triple: [Wyatt Tee Walker, spouse, Theresa Ann Walker]
-
A.
Theresa Ann Walker
chosen
Theresa Ann Walker is best known as the wife of prominent civil rights leader and Martin Luther King Jr. aide Wyatt Tee Walker.
-
B.
Theresa Ann Lane
Theresa Ann Lane is best known as the wife of legendary American country music singer and songwriter Merle Haggard.
-
C.
Theresa Galloway
Theresa Galloway is known as the wife of American war correspondent and author Joseph L. Galloway.
-
D.
Theresa Anne Bradley
Theresa Anne Bradley is known as the daughter of former U.S. Senator and Basketball Hall of Famer Bill Bradley.
-
E.
Jacqueline Ruth Weaver
Jacqueline Ruth Weaver is an Australian actress acclaimed for her work in film, television, and theatre, including her Oscar-nominated performances in "Animal Kingdom" and "Silver Linings Playbook."
- 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_69ca84defac48190abc1148804f184c1 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb22410208190b82b81a4df800f80 |
completed | April 2, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1e41725948190a40ddcf9552e9bf1 |
completed | April 5, 2026, 4:24 a.m. |
Created at: March 30, 2026, 8:30 p.m.