Triple
T18375928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intermission |
E446311
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Shirley Henderson |
—
|
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: Shirley Henderson | Statement: [Intermission, castMember, Shirley Henderson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shirley Henderson Context triple: [Intermission, castMember, Shirley Henderson]
-
A.
Shirley Henderson
chosen
Shirley Henderson is a Scottish actress known for her distinctive voice and roles in films such as the Bridget Jones series and the Harry Potter franchise.
-
B.
Sheila Hancock
Sheila Hancock is a British actress and author renowned for her extensive work in theatre, television, and film, as well as her appearances as a television presenter and panelist.
-
C.
Catherine Craig
Catherine Craig was an American film actress active in the 1940s, known for her supporting roles in Hollywood productions.
-
D.
Wendy Hiller
Wendy Hiller was an acclaimed English stage and film actress known for her nuanced, often understated performances in classics such as "Pygmalion" and "Separate Tables."
-
E.
Betsy Aidem
Betsy Aidem is an American actress known for her work in film, television, and theater.
- 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_69e51759353481908aa2de599fd2cf3b |
completed | April 19, 2026, 5:56 p.m. |
Created at: April 10, 2026, 10:45 a.m.