Triple
T24478120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnson Publishing Company |
E617287
|
entity |
| Predicate | spouseOfFounderInvolved |
P113119
|
FINISHED |
| Object | Eunice W. Johnson |
—
|
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: Eunice W. Johnson | Statement: [Johnson Publishing Company, spouseOfFounderInvolved, Eunice W. Johnson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOfFounderInvolved Context triple: [Johnson Publishing Company, spouseOfFounderInvolved, Eunice W. Johnson]
-
A.
spouseOfFounder
chosen
Indicates that one entity is the spouse (married partner) of the founder of another entity.
-
B.
spouseOfFounderOf
Indicates that one entity is the spouse of another entity who is the founder of a specified organization or entity.
-
C.
coFounderViaSpouseOf
Indicates that one entity is a co-founder of something by virtue of being the spouse of another co-founder, linking co-founding status through a marital relationship rather than direct founding activity.
-
D.
spouseInvolvedIn
Indicates that a person's spouse participates in, is associated with, or plays a role in a specified activity, event, or situation.
-
E.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
- 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_69e2d7f3ae788190b683394db15f220e |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29ed313a08190b745e89fe1c6cf55 |
completed | April 30, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f287d76c7c81909494f12e606a9149 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:21 a.m.