Triple
T35924840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diana Rauner |
E1038990
|
entity |
| Predicate | partnerInGovernment |
P109619
|
FINISHED |
| Object | Bruce Rauner |
—
|
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: Bruce Rauner | Statement: [Diana Rauner, partnerInGovernment, Bruce Rauner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partnerInGovernment Context triple: [Diana Rauner, partnerInGovernment, Bruce Rauner]
-
A.
partnerInGovernmentWith
Indicates that two entities share a formal partnership or coalition role within the same governmental structure or administration.
-
B.
partnerInMinistryWith
Indicates a collaborative relationship in which two or more entities work together in religious or spiritual ministry.
-
C.
governmentPartner
Indicates that one entity collaborates with or is formally partnered with a government or governmental body in some capacity.
-
D.
partnerInPolitics
chosen
Indicates that two entities are political partners, collaborating or aligned in political activities, campaigns, or governance.
-
E.
hostGovernmentCounterpart
Indicates that an entity serves as the official government counterpart or partner to the host entity in a given context or engagement.
- 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_69f76e2320748190b7f5c4750d0cd0d3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:07 p.m.