Triple
T21397557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neal Caffrey |
E527825
|
entity |
| Predicate | loveInterest |
P7325
|
FINISHED |
| Object | Sara Ellis |
—
|
NE NERFINISHED |
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: Sara Ellis | Statement: [Neal Caffrey, loveInterest, Sara Ellis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Ellis Context triple: [Neal Caffrey, loveInterest, Sara Ellis]
-
A.
Sara Ellis
chosen
Sara Ellis is a savvy insurance investigator and Neal Caffrey’s complex love interest in the television series "White Collar."
-
B.
Sara Kingsley
Sara Kingsley is a central character in the television sitcom "Grandfathered," around whom key family and comedic storylines revolve.
-
C.
Sara Howard
Sara Howard is a pioneering female secretary-turned-detective in 1890s New York City, featured prominently in Caleb Carr’s historical crime novel series "The Alienist."
-
D.
Sara Samuels
Sara Samuels is the central character in the "Black Mirror" episode "Arkangel," a young girl whose life is tightly controlled and surveilled through experimental parental technology.
-
E.
Sara Hess
Sara Hess is an American television writer and producer known for her work on acclaimed series such as House of the Dragon and Orange Is the New Black.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b520ee3c8190abddbee7e37e834c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b16a9c7c819083bd2d298106fdf1 |
completed | April 22, 2026, 11:30 a.m. |
Created at: April 16, 2026, 5:14 p.m.