Triple
T18404096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kelli Giddish |
E450073
|
entity |
| Predicate | notableRole |
P22
|
FINISHED |
| Object | Amanda Rollins |
—
|
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: Amanda Rollins | Statement: [Kelli Giddish, notableRole, Amanda Rollins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amanda Rollins Context triple: [Kelli Giddish, notableRole, Amanda Rollins]
-
A.
Amanda Rollins
chosen
Amanda Rollins is a fictional NYPD detective on Law & Order: Special Victims Unit who works closely with Olivia Benson on sex-crimes investigations.
-
B.
Amanda Clayton
Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
-
C.
Amanda Brown
Amanda Brown is an Australian musician best known as the multi-instrumentalist and violinist for the indie rock band The Go-Betweens.
-
D.
Amanda Thompson
Amanda Thompson is a prominent member of the Thompson family, known for her public profile and contributions that have brought recognition to the family name.
-
E.
Amanda Kramer
Amanda Kramer is an American filmmaker and writer known for her stylized, genre-bending independent films and theatrical, performance-driven storytelling.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e5195509cc8190bd4e91adb9b4a0ce |
completed | April 19, 2026, 6:05 p.m. |
Created at: April 10, 2026, 10:46 a.m.