Triple
T11222514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mildred Riddle |
E265606
|
entity |
| Predicate | spouseOfNotability |
P19181
|
FINISHED |
| Object | longest-serving justice in the history of the U.S. Supreme Court |
—
|
LITERAL 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: longest-serving justice in the history of the U.S. Supreme Court | Statement: [Mildred Riddle, spouseOfNotability, longest-serving justice in the history of the U.S. Supreme Court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOfNotability Context triple: [Mildred Riddle, spouseOfNotability, longest-serving justice in the history of the U.S. Supreme Court]
-
A.
spouseNotableFor
chosen
Indicates that a person's spouse is recognized or distinguished for a particular achievement, role, or characteristic.
-
B.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
C.
spouseNotableAward
Indicates that a person’s spouse has received a notable award or honor.
-
D.
marriedToNotablePerson
Indicates that a person is legally married to another individual who is widely recognized or notable.
-
E.
spouseAlsoKnownAs
Indicates that a person’s spouse is referred to by an alternative name or alias.
- 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8ec8fb08190b27144ab65f85957 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.