Triple
T20472373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth March |
E502223
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Eliza Scanlen |
—
|
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: Eliza Scanlen | Statement: [Elizabeth March, portrayedBy, Eliza Scanlen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eliza Scanlen Context triple: [Elizabeth March, portrayedBy, Eliza Scanlen]
-
A.
Eliza Scanlen
chosen
Eliza Scanlen is an Australian actress known for her roles in film and television, including prominent performances in projects like "Sharp Objects" and "Little Women."
-
B.
Emily Patterson
Emily Patterson is the daughter of American actress Téa Leoni.
-
C.
Katie Finneran
Katie Finneran is an American actress best known for her Tony Award–winning performances on Broadway and her work in television comedies and dramas.
-
D.
Alafair Burke
Alafair Burke is an American crime novelist, law professor, and former prosecutor known for her contemporary suspense novels and collaborations on bestselling mystery series.
-
E.
Gillian Murphy
Gillian Murphy is a renowned American ballet dancer and longtime principal with American Ballet Theatre, celebrated for her powerful technique and dramatic artistry.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6996197908190b6570e2a7fd6cf67 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.