Triple
T5948702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Brody |
E132342
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Sean Brody |
E151434
|
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: Sean Brody | Statement: [Michael Brody, sibling, Sean Brody]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sean Brody Context triple: [Michael Brody, sibling, Sean Brody]
-
A.
Sean Brody
chosen
Sean Brody is a fictional character from the "Jaws" film series, known as the younger son of police chief Martin Brody.
-
B.
Kevin Brodbin
Kevin Brodbin is a screenwriter known for his work on genre films, including the psychological thriller "Mindhunters."
-
C.
Dennis Burkley
Dennis Burkley was an American character actor known for his burly appearance and roles in numerous film and television productions from the 1970s through the early 2000s.
-
D.
Shawn Maurer
Shawn Maurer is a film cinematographer known for his work on parody and comedy movies, including the spoof film "Disaster Movie."
-
E.
Michael Brandt
Michael Brandt is an American screenwriter, director, and producer known for co-writing action films like "2 Fast 2 Furious" and for his work on television series such as "Chicago Fire."
- 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_69c0c08d4f0481908547609bc2736380 |
completed | March 23, 2026, 4:24 a.m. |
Created at: March 22, 2026, 4:01 p.m.