Triple
T5948717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Brody |
E132342
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Carla Brody |
E568986
|
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: Carla Brody | Statement: [Michael Brody, spouse, Carla Brody]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carla Brody Context triple: [Michael Brody, spouse, Carla Brody]
-
A.
Carla Brody
chosen
Carla Brody is a fictional character from the "Jaws" film series, known as the wife of police chief Martin Brody and mother of Michael and Sean Brody.
-
B.
Thea Brody
Thea Brody is a member of the Brody family, known primarily in relation to Michael Brody.
-
C.
Catherine Krouse Bauer
Catherine Krouse Bauer was an influential American public housing advocate and urban planner who helped shape U.S. housing policy during the New Deal era.
-
D.
Gloria Rudisch
Gloria Rudisch is an American pediatrician and public health official best known as the wife of artificial intelligence pioneer Marvin Minsky.
-
E.
Teresa Ganzel
Teresa Ganzel is an American actress and comedian best known for her frequent appearances on The Tonight Show Starring Johnny Carson and her roles in 1980s comedies and voice acting.
- 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_69c00869d3308190af89b2453e0f7546 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c0397deea08190b9397d0413740300 |
completed | March 22, 2026, 6:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c13557696881909b50c8b72af6878c |
completed | March 23, 2026, 12:43 p.m. |
Created at: March 22, 2026, 4:01 p.m.