Triple
T23860968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edith Willkie |
E592446
|
entity |
| Predicate | marriedToPresidentialCandidate |
P116912
|
FINISHED |
| Object | Wendell Willkie |
—
|
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: Wendell Willkie | Statement: [Edith Willkie, marriedToPresidentialCandidate, Wendell Willkie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriedToPresidentialCandidate Context triple: [Edith Willkie, marriedToPresidentialCandidate, Wendell Willkie]
-
A.
marriedToVicePresident
Indicates that one person is legally married to an individual who holds the office or role of vice president.
-
B.
marriedToPolitician
chosen
Indicates that a person is married to someone who holds or has held a political office or role.
-
C.
marriedToUSPresident
Indicates being legally married to an individual who holds or has held the office of President of the United States.
-
D.
marriedToDuringOffice
Indicates that one person was married to another person specifically during the time they held a particular office or position.
-
E.
marriedToFuturePresident
Indicates being married to someone who will later become president.
- F. None of above.
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_69e25d22eb488190914b193aff952e83 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1cadf91948190bed71376e6639294 |
completed | April 29, 2026, 9:09 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:12 p.m.