Triple
T19889595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Johnstone |
E477991
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Kiki Dee |
—
|
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: Kiki Dee | Statement: [Mrs Johnstone, portrayedBy, Kiki Dee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kiki Dee Context triple: [Mrs Johnstone, portrayedBy, Kiki Dee]
-
A.
Kiki Dee
chosen
Kiki Dee is an English singer best known for her 1976 duet with Elton John, "Don't Go Breaking My Heart," and for being one of the first British female artists signed to Motown.
-
B.
Sandy Shaw
Sandy Shaw is a screenwriter best known for co-writing the 1988 action thriller film "The Dead Pool" in the Dirty Harry series.
-
C.
Sylvia Dee
Sylvia Dee was an American lyricist best known for writing the words to popular mid-20th-century songs, including the hit ballad "Too Young."
-
D.
Niki Marvin
Niki Marvin is a film producer best known for producing the acclaimed 1994 drama "The Shawshank Redemption."
-
E.
Helen Hadley
Helen Hadley was the wife of American actor and narrator Reed Hadley.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590ce9f48190a51c0e5ecc828a06 |
completed | April 20, 2026, 4:49 p.m. |
Created at: April 10, 2026, 1:52 p.m.