Triple
T18378343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Never Let Go |
E446374
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Elizabeth Sellars |
—
|
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: Elizabeth Sellars | Statement: [Never Let Go, starring, Elizabeth Sellars]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Sellars Context triple: [Never Let Go, starring, Elizabeth Sellars]
-
A.
Elizabeth Sellars
chosen
Elizabeth Sellars was a Scottish actress known for her work in mid-20th-century British cinema and theatre, often appearing in literary adaptations and dramatic roles.
-
B.
Elizabeth Lail
Elizabeth Lail is an American actress best known for her roles in the TV series "You" and "Once Upon a Time."
-
C.
Milynn Sarley
Milynn Sarley is an American actress and internet personality known for her roles in low-budget fantasy and action films as well as her presence in online geek and gaming communities.
-
D.
Amy Eshleman
Amy Eshleman is an American former public librarian and education advocate best known as the wife of former Chicago mayor Lori Lightfoot.
-
E.
Laura Rister
Laura Rister is a film producer and executive known for her work on independent and prestige projects, including the financial thriller "Margin Call."
- 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_69d8b9f370b88190b1e5081c2c238e7f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e5179919c881908d55ea24f93c5827 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 10:45 a.m.