Triple
T946090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin Brody |
E20415
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Ellen Brody |
E78411
|
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: Ellen Brody | Statement: [Martin Brody, spouse, Ellen Brody]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ellen Brody Context triple: [Martin Brody, spouse, Ellen Brody]
-
A.
Ellen Brody
chosen
Ellen Brody is the resilient and protective wife of police chief Martin Brody in the Jaws film series, known for her role as a grounding family presence amid the shark-related terror.
-
B.
Barbara Robbins
Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
-
C.
Nancy Goodman
Nancy Goodman is an American diplomat, businesswoman, and philanthropist best known for founding the Susan G. Komen Breast Cancer Foundation.
-
D.
Audrey Bilger
Audrey Bilger is an American academic and administrator who serves as the president of Reed College in Portland, Oregon.
-
E.
Lynne Hollander
Lynne Hollander is an American activist best known for her involvement in the 1960s Free Speech Movement at UC Berkeley and her longtime partnership with fellow activist Mario Savio.
- 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_69a493b0f2fc81908cd227480a5356a1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3a61b648190b1b6c932e047e161 |
completed | March 1, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae65078b908190a75665a2ee025db6 |
completed | March 9, 2026, 6:13 a.m. |
Created at: March 1, 2026, 7:40 p.m.