Triple
T21367916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marian Clarke |
E526969
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Asia Booth Clarke |
—
|
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: Asia Booth Clarke | Statement: [Marian Clarke, relative, Asia Booth Clarke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asia Booth Clarke Context triple: [Marian Clarke, relative, Asia Booth Clarke]
-
A.
Asia Booth Clarke
chosen
Asia Booth Clarke was a 19th-century American writer and memoirist best known for her intimate accounts of the Booth theatrical family, including her brothers Edwin and John Wilkes Booth.
-
B.
Clare Douglas
Clare Douglas is a film editor known for her work on the British television drama "Gideon's Daughter."
-
C.
Jennifer Clarke
Jennifer Clarke is the wife of Peter Clarke.
-
D.
Clare Teal
Clare Teal is an English jazz and big band singer known for her rich vocals, interpretations of classic standards, and regular performances on BBC radio.
-
E.
Clare Bennett
Clare Bennett is a fictional character from the classic Hollywood musical film "Broadway Melody of 1940."
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee5baf5fb4819093f8d8afdd83ffdb |
completed | April 26, 2026, 6:38 p.m. |
Created at: April 16, 2026, 5:09 p.m.