Triple
T11571004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frankenstein (1931 film) |
E274384
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Mae Clarke |
E274387
|
NE FINISHED |
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: Mae Clarke | Statement: [Frankenstein (1931 film), starring, Mae Clarke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mae Clarke Context triple: [Frankenstein (1931 film), starring, Mae Clarke]
-
A.
Mae Clarke
chosen
Mae Clarke was an American film actress best known for her roles in early 1930s Hollywood classics, including Frankenstein and The Public Enemy.
-
B.
Rosanna Hoult
Rosanna Hoult is a British actress known for her work in film and television and as the sister of actor Nicholas Hoult.
-
C.
Rebecca Ferguson
Rebecca Ferguson is a Swedish actress known for her versatile performances in films such as the Mission: Impossible series, The Greatest Showman, and Dune.
-
D.
Saskia Reeves
Saskia Reeves is a British actress known for her work in film, television, and theatre, including roles in series such as "Luther" and numerous acclaimed stage productions.
-
E.
Katherine Waterston
Katherine Waterston is an American actress known for roles in films such as "Inherent Vice," the "Fantastic Beasts" series, and "Alien: Covenant."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd6913881908becf188c0a7a275 |
completed | April 10, 2026, 5:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e6e8dec908819080d97cd33be55b3f |
completed | April 21, 2026, 3:02 a.m. |
Created at: April 8, 2026, 9:38 p.m.