Triple
T18506959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Natalie Hurley |
E452221
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Sabrina Lloyd |
—
|
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: Sabrina Lloyd | Statement: [Natalie Hurley, portrayedBy, Sabrina Lloyd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sabrina Lloyd Context triple: [Natalie Hurley, portrayedBy, Sabrina Lloyd]
-
A.
Sabrina Lloyd
chosen
Sabrina Lloyd is an American actress best known for her roles on the television series "Sports Night" and "Sliders."
-
B.
Sabrina Hughes
Sabrina Hughes is known primarily as the daughter of former Australian Test cricket captain Kim Hughes.
-
C.
Sabrina Bryan
Sabrina Bryan is an American singer, actress, and dancer best known for starring in Disney Channel’s "The Cheetah Girls" franchise.
-
D.
Sabrina Ford
Sabrina Ford is an artificial intelligence researcher and entrepreneur best known as the founder of the Machine Intelligence Research Institute, an organization focused on the long-term safety and alignment of advanced AI systems.
-
E.
Sabrina Jalees
Sabrina Jalees is a Canadian comedian, actress, and writer known for her stand-up comedy and television roles, including a main role on the sitcom "Carol's Second Act."
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5334266708190b59aca3a2218c095 |
completed | April 19, 2026, 7:55 p.m. |
Created at: April 10, 2026, 11:36 a.m.