Triple
T14574648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lorraine Broughton |
E342009
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Sam Hart |
E241138
|
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: Sam Hart | Statement: [Lorraine Broughton, creator, Sam Hart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sam Hart Context triple: [Lorraine Broughton, creator, Sam Hart]
-
A.
Sam Hart
chosen
Sam Hart is a comic book artist best known for illustrating the graphic novel that inspired the film "Atomic Blonde."
-
B.
Leo Hunt
Leo Hunt is a fictional child character in the television series "Grey's Anatomy," known as the son of trauma surgeon Owen Hunt.
-
C.
Trig Taylor
Trig Taylor is a central character in the television drama series "The Chi," known for his involvement in the South Side Chicago community and his complex personal relationships.
-
D.
Ray Steele
Ray Steele is a fictional character in the "Fifty Shades" series, known as the loving adoptive father of protagonist Anastasia Steele.
-
E.
Jack Byrnes
Jack Byrnes is the overprotective ex-CIA father-in-law character played by Robert De Niro in the comedy film "Meet the Parents."
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f49d58819094fcd2a702e146cb |
completed | April 14, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd8acc788081909c41905785fa9a29 |
completed | May 8, 2026, 7:03 a.m. |
Created at: April 10, 2026, 1:24 a.m.