Triple
T7193087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stephen G. Breyer |
E167741
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Joanna Freda Hare |
E190185
|
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: Joanna Freda Hare | Statement: [Stephen G. Breyer, spouse, Joanna Freda Hare]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joanna Freda Hare Context triple: [Stephen G. Breyer, spouse, Joanna Freda Hare]
-
A.
Joanna Freda Hare Breyer
chosen
Joanna Freda Hare Breyer is a British-born psychologist and author known for her work with children facing serious illness and for being married to former U.S. Supreme Court Justice Stephen G. Breyer.
-
B.
Helen Morris
Helen Morris is an American book editor and the longtime wife of acclaimed film director Martin Scorsese.
-
C.
Frieda Lawrence
Frieda Lawrence was a German-born literary figure and muse best known as the wife and close collaborator of English novelist D. H. Lawrence.
-
D.
Winifred Gillis
Winifred Gillis is a fictional character from the American television sitcom "The Many Loves of Dobie Gillis."
-
E.
Helen Wood
Helen Wood is the wife of Scottish businessman and philanthropist Sir Ian Wood, former chairman of the Wood Group.
- 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_69c6888b5248819090499a884ee3ec39 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e9036544819083c70a5d2135ba4b |
completed | March 27, 2026, 8:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c861296e5c8190aa2a189e71963de9 |
completed | March 28, 2026, 11:15 p.m. |
Created at: March 27, 2026, 2:50 p.m.