Triple
T12874496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Kroc |
E307929
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Joan Kroc |
E1003486
|
NE 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: Joan Kroc | Statement: [Ray Kroc, spouse, Joan Kroc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joan Kroc Context triple: [Ray Kroc, spouse, Joan Kroc]
-
A.
Joan B. Kroc
chosen
Joan B. Kroc was an American philanthropist and widow of McDonald’s CEO Ray Kroc, renowned for her large-scale charitable donations to causes such as peace, education, and social justice.
-
B.
Helen Burger
Helen Burger was the wife of famed American bandleader Glenn Miller and the mother of their two children.
-
C.
Betty Smothers
Betty Smothers was a Baton Rouge police officer whose 1993 murder profoundly impacted her son, NFL running back Warrick Dunn, and inspired his extensive charitable work.
-
D.
Joan Hamburger
Joan Hamburger is a relative of American fashion designer Karl Anderson Jr., better known as Michael Kors.
-
E.
Myrtle Gruenert
Myrtle Gruenert was the wife of Australian speech therapist Lionel Logue, who famously treated King George VI.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d970f97f9c81908c75259a4cab1d3c |
completed | April 10, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69bb679f88190a1799b73c3f738b6 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:38 p.m.