Triple
T6571053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheila Sim |
E155436
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sheila Sim |
E155436
|
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: Sheila Sim | Statement: [Sheila Sim, name, Sheila Sim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sheila Sim Context triple: [Sheila Sim, name, Sheila Sim]
-
A.
Sheila Sim
chosen
Sheila Sim was a British actress and model best known for her film and stage work in the mid-20th century and her long association with the British theatre and film community.
-
B.
Anne Rennie
Anne Rennie is known as the wife of bestselling adventure novelist Wilbur Smith.
-
C.
Sheila Jordan
Sheila Jordan is an American jazz singer renowned for her bebop-influenced vocal style, innovative scat singing, and expressive interpretations of standards.
-
D.
Patricia Clarkson
Patricia Clarkson is an American actress acclaimed for her versatile performances in film, television, and theater, often in complex supporting roles.
-
E.
Joanne Dru
Joanne Dru was an American film and television actress best known for her roles in classic Westerns and dramas of the 1940s and 1950s.
- 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_69c688151254819080387f87deab8fa7 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae5791e881909d0b340aa63c6223 |
completed | March 27, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70ae438b0819086449c169e5c7e49 |
completed | March 27, 2026, 10:55 p.m. |
Created at: March 27, 2026, 1:53 p.m.