Triple
T34528124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Caroline Clinton Duke |
E886458
|
entity |
| Predicate | spouse's notable role |
P19181
|
FINISHED |
| Object | American industrialist |
—
|
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: American industrialist | Statement: [Mary Caroline Clinton Duke, spouse's notable role, American industrialist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouse's notable role Context triple: [Mary Caroline Clinton Duke, spouse's notable role, American industrialist]
-
A.
spouseNotableFor
chosen
Indicates that a person's spouse is recognized or distinguished for a particular achievement, role, or characteristic.
-
B.
spouseRoleInHistory
Indicates that one entity serves or is recognized as the spouse of another entity within a specific historical context or period.
-
C.
spouse notableWork
Indicates that a person's spouse is significantly associated with a particular notable work.
-
D.
spouseOfRole
Indicates that one role is the spouse (husband, wife, or equivalent marital partner) of another role.
-
E.
spouseNotableWorkField
Indicates that the notable work or professional field associated with a person’s spouse is being specified.
- 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_69f349cd7c148190aa99192b126d1527 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fe00dad1708190b6522476bebb43af |
completed | May 8, 2026, 3:27 p.m. |
| PD | Predicate disambiguation | batch_69fdfc3717f48190bb50ac2919c8ef95 |
completed | May 8, 2026, 3:07 p.m. |
Created at: May 1, 2026, 2:02 a.m.